essay about your conclusion

17 Essay Conclusion Examples (Copy and Paste)

Essay conclusions are not just extra filler. They are important because they tie together your arguments, then give you the chance to forcefully drive your point home.

I created the 5 Cs conclusion method to help you write essay conclusions:

I’ve previously produced the video below on how to write a conclusion that goes over the above image.

The video follows the 5 C’s method ( you can read about it in this post ), which doesn’t perfectly match each of the below copy-and-paste conclusion examples, but the principles are similar, and can help you to write your own strong conclusion:

💡 New! Try this AI Prompt to Generate a Sample 5Cs Conclusion This is my essay: [INSERT ESSAY WITHOUT THE CONCLUSION]. I want you to write a conclusion for this essay. In the first sentence of the conclusion, return to a statement I made in the introduction. In the second sentence, reiterate the thesis statement I have used. In the third sentence, clarify how my final position is relevant to the Essay Question, which is [ESSAY QUESTION]. In the fourth sentence, explain who should be interested in my findings. In the fifth sentence, end by noting in one final, engaging sentence why this topic is of such importance.

Remember: The prompt can help you generate samples but you can’t submit AI text for assessment. Make sure you write your conclusion in your own words.

Essay Conclusion Examples

Below is a range of copy-and-paste essay conclusions with gaps for you to fill-in your topic and key arguments. Browse through for one you like (there are 17 for argumentative, expository, compare and contrast, and critical essays). Once you’ve found one you like, copy it and add-in the key points to make it your own.

1. Argumentative Essay Conclusions

The arguments presented in this essay demonstrate the significant importance of _____________. While there are some strong counterarguments, such as ____________, it remains clear that the benefits/merits of _____________ far outweigh the potential downsides. The evidence presented throughout the essay strongly support _____________. In the coming years, _____________ will be increasingly important. Therefore, continual advocacy for the position presented in this essay will be necessary, especially due to its significant implications for _____________.

Version 1 Filled-In

The arguments presented in this essay demonstrate the significant importance of fighting climate change. While there are some strong counterarguments, such as the claim that it is too late to stop catastrophic change, it remains clear that the merits of taking drastic action far outweigh the potential downsides. The evidence presented throughout the essay strongly support the claim that we can at least mitigate the worst effects. In the coming years, intergovernmental worldwide agreements will be increasingly important. Therefore, continual advocacy for the position presented in this essay will be necessary, especially due to its significant implications for humankind.

As this essay has shown, it is clear that the debate surrounding _____________ is multifaceted and highly complex. While there are strong arguments opposing the position that _____________, there remains overwhelming evidence to support the claim that _____________. A careful analysis of the empirical evidence suggests that _____________ not only leads to ____________, but it may also be a necessity for _____________. Moving forward, _____________ should be a priority for all stakeholders involved, as it promises a better future for _____________. The focus should now shift towards how best to integrate _____________ more effectively into society.

Version 2 Filled-In

As this essay has shown, it is clear that the debate surrounding climate change is multifaceted and highly complex. While there are strong arguments opposing the position that we should fight climate change, there remains overwhelming evidence to support the claim that action can mitigate the worst effects. A careful analysis of the empirical evidence suggests that strong action not only leads to better economic outcomes in the long term, but it may also be a necessity for preventing climate-related deaths. Moving forward, carbon emission mitigation should be a priority for all stakeholders involved, as it promises a better future for all. The focus should now shift towards how best to integrate smart climate policies more effectively into society.

Based upon the preponderance of evidence, it is evident that _____________ holds the potential to significantly alter/improve _____________. The counterarguments, while noteworthy, fail to diminish the compelling case for _____________. Following an examination of both sides of the argument, it has become clear that _____________ presents the most effective solution/approach to _____________. Consequently, it is imperative that society acknowledge the value of _____________ for developing a better  _____________. Failing to address this topic could lead to negative outcomes, including _____________.

Version 3 Filled-In

Based upon the preponderance of evidence, it is evident that addressing climate change holds the potential to significantly improve the future of society. The counterarguments, while noteworthy, fail to diminish the compelling case for immediate climate action. Following an examination of both sides of the argument, it has become clear that widespread and urgent social action presents the most effective solution to this pressing problem. Consequently, it is imperative that society acknowledge the value of taking immediate action for developing a better environment for future generations. Failing to address this topic could lead to negative outcomes, including more extreme climate events and greater economic externalities.

See Also: Examples of Counterarguments

On the balance of evidence, there is an overwhelming case for _____________. While the counterarguments offer valid points that are worth examining, they do not outweigh or overcome the argument that _____________. An evaluation of both perspectives on this topic concludes that _____________ is the most sufficient option for  _____________. The implications of embracing _____________ do not only have immediate benefits, but they also pave the way for a more _____________. Therefore, the solution of _____________ should be actively pursued by _____________.

Version 4 Filled-In

On the balance of evidence, there is an overwhelming case for immediate tax-based action to mitigate the effects of climate change. While the counterarguments offer valid points that are worth examining, they do not outweigh or overcome the argument that action is urgently necessary. An evaluation of both perspectives on this topic concludes that taking societal-wide action is the most sufficient option for  achieving the best results. The implications of embracing a society-wide approach like a carbon tax do not only have immediate benefits, but they also pave the way for a more healthy future. Therefore, the solution of a carbon tax or equivalent policy should be actively pursued by governments.

2. Expository Essay Conclusions

Overall, it is evident that _____________ plays a crucial role in _____________. The analysis presented in this essay demonstrates the clear impact of _____________ on _____________. By understanding the key facts about _____________, practitioners/society are better equipped to navigate _____________. Moving forward, further exploration of _____________ will yield additional insights and information about _____________. As such, _____________ should remain a focal point for further discussions and studies on _____________.

Overall, it is evident that social media plays a crucial role in harming teenagers’ mental health. The analysis presented in this essay demonstrates the clear impact of social media on young people. By understanding the key facts about the ways social media cause young people to experience body dysmorphia, teachers and parents are better equipped to help young people navigate online spaces. Moving forward, further exploration of the ways social media cause harm will yield additional insights and information about how it can be more sufficiently regulated. As such, the effects of social media on youth should remain a focal point for further discussions and studies on youth mental health.

To conclude, this essay has explored the multi-faceted aspects of _____________. Through a careful examination of _____________, this essay has illuminated its significant influence on _____________. This understanding allows society to appreciate the idea that _____________. As research continues to emerge, the importance of _____________ will only continue to grow. Therefore, an understanding of _____________ is not merely desirable, but imperative for _____________.

To conclude, this essay has explored the multi-faceted aspects of globalization. Through a careful examination of globalization, this essay has illuminated its significant influence on the economy, cultures, and society. This understanding allows society to appreciate the idea that globalization has both positive and negative effects. As research continues to emerge, the importance of studying globalization will only continue to grow. Therefore, an understanding of globalization’s effects is not merely desirable, but imperative for judging whether it is good or bad.

Reflecting on the discussion, it is clear that _____________ serves a pivotal role in _____________. By delving into the intricacies of _____________, we have gained valuable insights into its impact and significance. This knowledge will undoubtedly serve as a guiding principle in _____________. Moving forward, it is paramount to remain open to further explorations and studies on _____________. In this way, our understanding and appreciation of _____________ can only deepen and expand.

Reflecting on the discussion, it is clear that mass media serves a pivotal role in shaping public opinion. By delving into the intricacies of mass media, we have gained valuable insights into its impact and significance. This knowledge will undoubtedly serve as a guiding principle in shaping the media landscape. Moving forward, it is paramount to remain open to further explorations and studies on how mass media impacts society. In this way, our understanding and appreciation of mass media’s impacts can only deepen and expand.

In conclusion, this essay has shed light on the importance of _____________ in the context of _____________. The evidence and analysis provided underscore the profound effect _____________ has on _____________. The knowledge gained from exploring _____________ will undoubtedly contribute to more informed and effective decisions in _____________. As we continue to progress, the significance of understanding _____________ will remain paramount. Hence, we should strive to deepen our knowledge of _____________ to better navigate and influence _____________.

In conclusion, this essay has shed light on the importance of bedside manner in the context of nursing. The evidence and analysis provided underscore the profound effect compassionate bedside manner has on patient outcome. The knowledge gained from exploring nurses’ bedside manner will undoubtedly contribute to more informed and effective decisions in nursing practice. As we continue to progress, the significance of understanding nurses’ bedside manner will remain paramount. Hence, we should strive to deepen our knowledge of this topic to better navigate and influence patient outcomes.

See More: How to Write an Expository Essay

3. Compare and Contrast Essay Conclusion

While both _____________ and _____________ have similarities such as _____________, they also have some very important differences in areas like _____________. Through this comparative analysis, a broader understanding of _____________ and _____________ has been attained. The choice between the two will largely depend on _____________. For example, as highlighted in the essay, ____________. Despite their differences, both _____________ and _____________ have value in different situations.

While both macrosociology and microsociology have similarities such as their foci on how society is structured, they also have some very important differences in areas like their differing approaches to research methodologies. Through this comparative analysis, a broader understanding of macrosociology and microsociology has been attained. The choice between the two will largely depend on the researcher’s perspective on how society works. For example, as highlighted in the essay, microsociology is much more concerned with individuals’ experiences while macrosociology is more concerned with social structures. Despite their differences, both macrosociology and microsociology have value in different situations.

It is clear that _____________ and _____________, while seeming to be different, have shared characteristics in _____________. On the other hand, their contrasts in _____________ shed light on their unique features. The analysis provides a more nuanced comprehension of these subjects. In choosing between the two, consideration should be given to _____________. Despite their disparities, it’s crucial to acknowledge the importance of both when it comes to _____________.

It is clear that behaviorism and consructivism, while seeming to be different, have shared characteristics in their foci on knowledge acquisition over time. On the other hand, their contrasts in ideas about the role of experience in learning shed light on their unique features. The analysis provides a more nuanced comprehension of these subjects. In choosing between the two, consideration should be given to which approach works best in which situation. Despite their disparities, it’s crucial to acknowledge the importance of both when it comes to student education.

Reflecting on the points discussed, it’s evident that _____________ and _____________ share similarities such as _____________, while also demonstrating unique differences, particularly in _____________. The preference for one over the other would typically depend on factors such as _____________. Yet, regardless of their distinctions, both _____________ and _____________ play integral roles in their respective areas, significantly contributing to _____________.

Reflecting on the points discussed, it’s evident that red and orange share similarities such as the fact they are both ‘hot colors’, while also demonstrating unique differences, particularly in their social meaning (red meaning danger and orange warmth). The preference for one over the other would typically depend on factors such as personal taste. Yet, regardless of their distinctions, both red and orange play integral roles in their respective areas, significantly contributing to color theory.

Ultimately, the comparison and contrast of _____________ and _____________ have revealed intriguing similarities and notable differences. Differences such as _____________ give deeper insights into their unique and shared qualities. When it comes to choosing between them, _____________ will likely be a deciding factor. Despite these differences, it is important to remember that both _____________ and _____________ hold significant value within the context of _____________, and each contributes to _____________ in its own unique way.

Ultimately, the comparison and contrast of driving and flying have revealed intriguing similarities and notable differences. Differences such as their differing speed to destination give deeper insights into their unique and shared qualities. When it comes to choosing between them, urgency to arrive at the destination will likely be a deciding factor. Despite these differences, it is important to remember that both driving and flying hold significant value within the context of air transit, and each contributes to facilitating movement in its own unique way.

See Here for More Compare and Contrast Essay Examples

4. Critical Essay Conclusion

In conclusion, the analysis of _____________ has unveiled critical aspects related to _____________. While there are strengths in _____________, its limitations are equally telling. This critique provides a more informed perspective on _____________, revealing that there is much more beneath the surface. Moving forward, the understanding of _____________ should evolve, considering both its merits and flaws.

In conclusion, the analysis of flow theory has unveiled critical aspects related to motivation and focus. While there are strengths in achieving a flow state, its limitations are equally telling. This critique provides a more informed perspective on how humans achieve motivation, revealing that there is much more beneath the surface. Moving forward, the understanding of flow theory of motivation should evolve, considering both its merits and flaws.

To conclude, this critical examination of _____________ sheds light on its multi-dimensional nature. While _____________ presents notable advantages, it is not without its drawbacks. This in-depth critique offers a comprehensive understanding of _____________. Therefore, future engagements with _____________ should involve a balanced consideration of its strengths and weaknesses.

To conclude, this critical examination of postmodern art sheds light on its multi-dimensional nature. While postmodernism presents notable advantages, it is not without its drawbacks. This in-depth critique offers a comprehensive understanding of how it has contributed to the arts over the past 50 years. Therefore, future engagements with postmodern art should involve a balanced consideration of its strengths and weaknesses.

Upon reflection, the critique of _____________ uncovers profound insights into its underlying intricacies. Despite its positive aspects such as ________, it’s impossible to overlook its shortcomings. This analysis provides a nuanced understanding of _____________, highlighting the necessity for a balanced approach in future interactions. Indeed, both the strengths and weaknesses of _____________ should be taken into account when considering ____________.

Upon reflection, the critique of marxism uncovers profound insights into its underlying intricacies. Despite its positive aspects such as its ability to critique exploitation of labor, it’s impossible to overlook its shortcomings. This analysis provides a nuanced understanding of marxism’s harmful effects when used as an economic theory, highlighting the necessity for a balanced approach in future interactions. Indeed, both the strengths and weaknesses of marxism should be taken into account when considering the use of its ideas in real life.

Ultimately, this critique of _____________ offers a detailed look into its advantages and disadvantages. The strengths of _____________ such as __________ are significant, yet its limitations such as _________ are not insignificant. This balanced analysis not only offers a deeper understanding of _____________ but also underscores the importance of critical evaluation. Hence, it’s crucial that future discussions around _____________ continue to embrace this balanced approach.

Ultimately, this critique of artificial intelligence offers a detailed look into its advantages and disadvantages. The strengths of artificial intelligence, such as its ability to improve productivity are significant, yet its limitations such as the possibility of mass job losses are not insignificant. This balanced analysis not only offers a deeper understanding of artificial intelligence but also underscores the importance of critical evaluation. Hence, it’s crucial that future discussions around the regulation of artificial intelligence continue to embrace this balanced approach.

This article promised 17 essay conclusions, and this one you are reading now is the twenty-first. This last conclusion demonstrates that the very best essay conclusions are written uniquely, from scratch, in order to perfectly cater the conclusion to the topic. A good conclusion will tie together all the key points you made in your essay and forcefully drive home the importance or relevance of your argument, thesis statement, or simply your topic so the reader is left with one strong final point to ponder.

Chris Drew (PhD)

Dr. Chris Drew is the founder of the Helpful Professor. He holds a PhD in education and has published over 20 articles in scholarly journals. He is the former editor of the Journal of Learning Development in Higher Education. [Image Descriptor: Photo of Chris]

• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd/ 15 Self-Actualization Examples (Maslow's Hierarchy)
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd/ Forest Schools Philosophy & Curriculum, Explained!
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd/ Montessori's 4 Planes of Development, Explained!
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd/ Montessori vs Reggio Emilia vs Steiner-Waldorf vs Froebel

Leave a Comment Cancel Reply

Your email address will not be published. Required fields are marked *

In a short paper—even a research paper—you don’t need to provide an exhaustive summary as part of your conclusion. But you do need to make some kind of transition between your final body paragraph and your concluding paragraph. This may come in the form of a few sentences of summary. Or it may come in the form of a sentence that brings your readers back to your thesis or main idea and reminds your readers where you began and how far you have traveled.

So, for example, in a paper about the relationship between ADHD and rejection sensitivity, Vanessa Roser begins by introducing readers to the fact that researchers have studied the relationship between the two conditions and then provides her explanation of that relationship. Here’s her thesis: “While socialization may indeed be an important factor in RS, I argue that individuals with ADHD may also possess a neurological predisposition to RS that is exacerbated by the differing executive and emotional regulation characteristic of ADHD.”

In her final paragraph, Roser reminds us of where she started by echoing her thesis: “This literature demonstrates that, as with many other conditions, ADHD and RS share a delicately intertwined pattern of neurological similarities that is rooted in the innate biology of an individual’s mind, a connection that cannot be explained in full by the behavioral mediation hypothesis.”  

Highlight the “so what”  

At the beginning of your paper, you explain to your readers what’s at stake—why they should care about the argument you’re making. In your conclusion, you can bring readers back to those stakes by reminding them why your argument is important in the first place. You can also draft a few sentences that put those stakes into a new or broader context.

In the conclusion to her paper about ADHD and RS, Roser echoes the stakes she established in her introduction—that research into connections between ADHD and RS has led to contradictory results, raising questions about the “behavioral mediation hypothesis.”

She writes, “as with many other conditions, ADHD and RS share a delicately intertwined pattern of neurological similarities that is rooted in the innate biology of an individual’s mind, a connection that cannot be explained in full by the behavioral mediation hypothesis.”  

Leave your readers with the “now what”  

After the “what” and the “so what,” you should leave your reader with some final thoughts. If you have written a strong introduction, your readers will know why you have been arguing what you have been arguing—and why they should care. And if you’ve made a good case for your thesis, then your readers should be in a position to see things in a new way, understand new questions, or be ready for something that they weren’t ready for before they read your paper.

In her conclusion, Roser offers two “now what” statements. First, she explains that it is important to recognize that the flawed behavioral mediation hypothesis “seems to place a degree of fault on the individual. It implies that individuals with ADHD must have elicited such frequent or intense rejection by virtue of their inadequate social skills, erasing the possibility that they may simply possess a natural sensitivity to emotion.” She then highlights the broader implications for treatment of people with ADHD, noting that recognizing the actual connection between rejection sensitivity and ADHD “has profound implications for understanding how individuals with ADHD might best be treated in educational settings, by counselors, family, peers, or even society as a whole.”

To find your own “now what” for your essay’s conclusion, try asking yourself these questions:

• What can my readers now understand, see in a new light, or grapple with that they would not have understood in the same way before reading my paper? Are we a step closer to understanding a larger phenomenon or to understanding why what was at stake is so important?  
• What questions can I now raise that would not have made sense at the beginning of my paper? Questions for further research? Other ways that this topic could be approached?  
• Are there other applications for my research? Could my questions be asked about different data in a different context? Could I use my methods to answer a different question?  
• What action should be taken in light of this argument? What action do I predict will be taken or could lead to a solution?  
• What larger context might my argument be a part of?  

What to avoid in your conclusion  

• a complete restatement of all that you have said in your paper.  
• a substantial counterargument that you do not have space to refute; you should introduce counterarguments before your conclusion.  
• an apology for what you have not said. If you need to explain the scope of your paper, you should do this sooner—but don’t apologize for what you have not discussed in your paper.  
• fake transitions like “in conclusion” that are followed by sentences that aren’t actually conclusions. (“In conclusion, I have now demonstrated that my thesis is correct.”)
• picture_as_pdf Conclusions

How to Write a Conclusion for an Essay - Tips and Examples

The conclusion of your essay is like the grand finale of a fireworks display. It's the last impression you leave on your reader, the moment that ties everything together and leaves them with a lasting impact. 

But for many writers, crafting a conclusion can feel like an afterthought, a hurdle to jump after the excitement of developing the main body of their work. Fear not! This article will equip you with the tools and techniques regarding how to write a conclusion for an essay that effectively summarizes your main points, strengthens your argument, and leaves your reader feeling satisfied and engaged.

What Is a Conclusion

In an essay, the conclusion acts as your final curtain call. It's where you revisit your initial claim (thesis), condense your main supporting arguments, and leave the reader with a lasting takeaway. 

Imagine it as the bridge that connects your ideas to a broader significance. A well-crafted conclusion does more than simply summarize; it elevates your points and offers a sense of closure, ensuring the reader leaves with a clear understanding of your argument's impact. In the next section, you will find conclusion ideas that you could use for your essay.

Please note that our online paper writing service can provide you not only with a stand-alone conclusion but with a fully new composition as well!

Types of Conclusion

Here's a breakdown of various conclusion types, each serving a distinct purpose:

How Long Should a Conclusion Be

The ideal length of a conclusion depends on the overall length of your essay, but there are some general guidelines:

• Shorter Essays (500-750 words): Aim for 3-5 sentences. This ensures you effectively wrap up your points without adding unnecessary content.
• Medium Essays (750-1200 words): Here, you can expand to 5-8 sentences. This provides more space to elaborate on your concluding thought or call to action.
• Longer Essays (1200+ words): For these, you can have a conclusion of 8-10 sentences. This allows for a more comprehensive summary or a more nuanced exploration of the future implications or broader significance of your topic.

Here are some additional factors to consider:

• The complexity of your argument: If your essay explores a multifaceted topic, your conclusion might need to be slightly longer to address all the points adequately.
• Type of conclusion: A call to action or a hypothetical scenario might require a few extra sentences for elaboration compared to a simple summary.

Remember: The most important aspect is ensuring your conclusion effectively summarizes your main points, leaves a lasting impression, and doesn't feel rushed or tacked on.

Here's a helpful rule of thumb:

• Keep it proportional: Your conclusion should be roughly 5-10% of your total essay length.

How many sentences should a conclusion be?

Conclusion Transition Words

Transition words for conclusion act like signposts for your reader. They smoothly guide them from the main body of your essay to your closing thoughts, ensuring a clear and logical flow of ideas. Here are some transition words specifically suited for concluding your essay:

Remember, the best transition word will depend on the specific type of conclusion you're aiming for.

How to Write a Conclusion

Every essay or dissertation writer knows that the toughest part of working on a conclusion can be striking the right balance. You want to effectively summarize your main points without redundancy, leaving a lasting impression that feels fresh and impactful, all within a concise and focused section. Here’s a step-by-step guide to help you write a stunning essay conclusion:

Restate Your Thesis

Briefly remind your reader of your essay's central claim. This doesn't have to be a word-for-word repetition but a concise restatement that refreshes their memory.

Summarize Key Points

In a few sentences, revisit the main arguments you used to support your thesis. When writing a conclusion, don't get bogged down in details, but offer a high-level overview that reinforces your essay's focus.

Leave a Lasting Impression

This is where your knowledge of how to write a good conclusion can shine! Consider a thought-provoking question, a call to action, or a connection to a broader truth—something that lingers in the reader's mind and resonates beyond the final sentence.

Avoid Introducing New Information

The conclusion paragraph shouldn't introduce entirely new ideas. Stick to wrapping up your existing arguments and leaving a final thought.

Ensure Flow and Readability

Transition smoothly from the main body of your essay to the conclusion. Use transition words like "in conclusion," "finally," or "as a result," and ensure your closing sentences feel natural and well-connected to the rest of your work.

Note that you can simply buy essay at any time and focus on other more important assignments or just enjoy your free time.

Conclusion Paragraph Outline

Here's an outline to help you better understand how to write a conclusion paragraph:

• Tailor the length of your conclusion to your essay's overall length (shorter essays: 3-5 sentences, longer essays: 8-10 sentences).
• Ensure a smooth transition from the main body using transition words.
• Avoid introducing new information; focus on wrapping up your existing points.
• Proofread for clarity and ensure your conclusion ties everything together and delivers a final impactful statement.

Read more: Persuasive essay outline . 

Do’s and Don’ts of Essay Conclusion Writing

According to professional term paper writers , a strong conclusion is essential for leaving a lasting impression on your reader. Here's a list of action items you should and shouldn’t do when writing an essay conclusion:

Want to Have Better Grades?

Address to our professionals and get your task done asap!

Conclusion Examples

A strong conclusion isn't just an afterthought – it's the capstone of your essay. Here are five examples of conclusion paragraphs for essays showcasing different techniques to craft a powerful closing to make your essay stand out.

1. Call to Action: (Essay About the Importance of Recycling)

In conclusion, the environmental impact of our waste is undeniable. We all have a responsibility to adopt sustainable practices. We can collectively make a significant difference by incorporating simple changes like recycling into our daily routines. Join the movement – choose to reuse, reduce, and recycle.

2. Provocative Question: (Essay Exploring the Potential Consequences of Artificial Intelligence)

As artificial intelligence rapidly evolves, it's crucial to consider its impact on humanity. While AI holds immense potential for progress, will it remain a tool for good, or will it eventually surpass human control? This question demands our collective attention, as the decisions we make today will shape the future of AI and its impact on our world.

3. Universal Insight: (Essay Analyzing a Historical Event)

The study of history offers valuable lessons that transcend time. The events of the [insert historical event] remind us that even small acts of defiance can have a ripple effect, inspiring change and ultimately leading to a brighter future. Every voice has the power to make a difference, and courage can be contagious.

4. Future Implications: (Essay Discussing the Rise of Social Media)

Social media's explosive growth has transformed how we connect and consume information. While these platforms offer undeniable benefits, their long-term effects on social interaction, mental health, and political discourse require careful consideration. As social media continues to evolve, we must remain vigilant and ensure it remains a tool for positive connection and not a source of division.

5. Hypothetical Scenario: (Essay Arguing for the Importance of Space Exploration)

Imagine a world where our understanding of the universe is limited to Earth. We miss out on the potential for groundbreaking discoveries in physics, medicine, and our place in the cosmos. By continuing to venture beyond our planet, we push the boundaries of human knowledge and inspire future generations to reach for the stars.

Recommended for reading: Nursing essay examples .

Difference Between Good and Weak Conclusions

Not all conclusions are created equal. A weak ending can leave your reader feeling stranded, unsure of where your essay has taken them. Conversely, writing a conclusion that is strong acts as a landing pad, summarizing your key points and leaving a lasting impression.

Nailed that essay? Don't blow it with a lame ending! A good conclusion is like the mic drop at the end of a rap song. It reminds the reader of your main points but in a cool new way. Throw in a thought-provoking question, a call to action, or a connection to something bigger, and you'll leave them thinking long after they turn the page.

Need Help with Your Essays?

Our service is the best assistant the money can buy – original and reliable. 

How To Write A Conclusion For An Essay?

How to write a good conclusion, how to write a conclusion for a college essay.

Daniel Parker

is a seasoned educational writer focusing on scholarship guidance, research papers, and various forms of academic essays including reflective and narrative essays. His expertise also extends to detailed case studies. A scholar with a background in English Literature and Education, Daniel’s work on EssayPro blog aims to support students in achieving academic excellence and securing scholarships. His hobbies include reading classic literature and participating in academic forums.

is an expert in nursing and healthcare, with a strong background in history, law, and literature. Holding advanced degrees in nursing and public health, his analytical approach and comprehensive knowledge help students navigate complex topics. On EssayPro blog, Adam provides insightful articles on everything from historical analysis to the intricacies of healthcare policies. In his downtime, he enjoys historical documentaries and volunteering at local clinics.

• Updated writing tips.
• Added informative tables.
• Added conclusion example.
• Added an article conclusion.
• Essay Conclusions | UMGC. (n.d.). University of Maryland Global Campus. https://www.umgc.edu/current-students/learning-resources/writing-center/writing-resources/writing/essay-conclusions
• How to Write a Conclusion for an Essay | BestColleges. (n.d.). BestColleges.com. https://www.bestcolleges.com/blog/how-to-write-a-conclusion/
• Ending the Essay: Conclusions | Harvard College Writing Center. (n.d.). https://writingcenter.fas.harvard.edu/pages/ending-essay-conclusions

Related Articles

Conclusions

What this handout is about.

This handout will explain the functions of conclusions, offer strategies for writing effective ones, help you evaluate conclusions you’ve drafted, and suggest approaches to avoid.

About conclusions

Introductions and conclusions can be difficult to write, but they’re worth investing time in. They can have a significant influence on a reader’s experience of your paper.

Just as your introduction acts as a bridge that transports your readers from their own lives into the “place” of your analysis, your conclusion can provide a bridge to help your readers make the transition back to their daily lives. Such a conclusion will help them see why all your analysis and information should matter to them after they put the paper down.

Your conclusion is your chance to have the last word on the subject. The conclusion allows you to have the final say on the issues you have raised in your paper, to synthesize your thoughts, to demonstrate the importance of your ideas, and to propel your reader to a new view of the subject. It is also your opportunity to make a good final impression and to end on a positive note.

Your conclusion can go beyond the confines of the assignment. The conclusion pushes beyond the boundaries of the prompt and allows you to consider broader issues, make new connections, and elaborate on the significance of your findings.

Your conclusion should make your readers glad they read your paper. Your conclusion gives your reader something to take away that will help them see things differently or appreciate your topic in personally relevant ways. It can suggest broader implications that will not only interest your reader, but also enrich your reader’s life in some way. It is your gift to the reader.

Strategies for writing an effective conclusion

One or more of the following strategies may help you write an effective conclusion:

• Play the “So What” Game. If you’re stuck and feel like your conclusion isn’t saying anything new or interesting, ask a friend to read it with you. Whenever you make a statement from your conclusion, ask the friend to say, “So what?” or “Why should anybody care?” Then ponder that question and answer it. Here’s how it might go: You: Basically, I’m just saying that education was important to Douglass. Friend: So what? You: Well, it was important because it was a key to him feeling like a free and equal citizen. Friend: Why should anybody care? You: That’s important because plantation owners tried to keep slaves from being educated so that they could maintain control. When Douglass obtained an education, he undermined that control personally. You can also use this strategy on your own, asking yourself “So What?” as you develop your ideas or your draft.
• Return to the theme or themes in the introduction. This strategy brings the reader full circle. For example, if you begin by describing a scenario, you can end with the same scenario as proof that your essay is helpful in creating a new understanding. You may also refer to the introductory paragraph by using key words or parallel concepts and images that you also used in the introduction.
• Synthesize, don’t summarize. Include a brief summary of the paper’s main points, but don’t simply repeat things that were in your paper. Instead, show your reader how the points you made and the support and examples you used fit together. Pull it all together.
• Include a provocative insight or quotation from the research or reading you did for your paper.
• Propose a course of action, a solution to an issue, or questions for further study. This can redirect your reader’s thought process and help them to apply your info and ideas to their own life or to see the broader implications.
• Point to broader implications. For example, if your paper examines the Greensboro sit-ins or another event in the Civil Rights Movement, you could point out its impact on the Civil Rights Movement as a whole. A paper about the style of writer Virginia Woolf could point to her influence on other writers or on later feminists.

Strategies to avoid

• Beginning with an unnecessary, overused phrase such as “in conclusion,” “in summary,” or “in closing.” Although these phrases can work in speeches, they come across as wooden and trite in writing.
• Stating the thesis for the very first time in the conclusion.
• Introducing a new idea or subtopic in your conclusion.
• Ending with a rephrased thesis statement without any substantive changes.
• Making sentimental, emotional appeals that are out of character with the rest of an analytical paper.
• Including evidence (quotations, statistics, etc.) that should be in the body of the paper.

Four kinds of ineffective conclusions

• The “That’s My Story and I’m Sticking to It” Conclusion. This conclusion just restates the thesis and is usually painfully short. It does not push the ideas forward. People write this kind of conclusion when they can’t think of anything else to say. Example: In conclusion, Frederick Douglass was, as we have seen, a pioneer in American education, proving that education was a major force for social change with regard to slavery.
• The “Sherlock Holmes” Conclusion. Sometimes writers will state the thesis for the very first time in the conclusion. You might be tempted to use this strategy if you don’t want to give everything away too early in your paper. You may think it would be more dramatic to keep the reader in the dark until the end and then “wow” them with your main idea, as in a Sherlock Holmes mystery. The reader, however, does not expect a mystery, but an analytical discussion of your topic in an academic style, with the main argument (thesis) stated up front. Example: (After a paper that lists numerous incidents from the book but never says what these incidents reveal about Douglass and his views on education): So, as the evidence above demonstrates, Douglass saw education as a way to undermine the slaveholders’ power and also an important step toward freedom.
• The “America the Beautiful”/”I Am Woman”/”We Shall Overcome” Conclusion. This kind of conclusion usually draws on emotion to make its appeal, but while this emotion and even sentimentality may be very heartfelt, it is usually out of character with the rest of an analytical paper. A more sophisticated commentary, rather than emotional praise, would be a more fitting tribute to the topic. Example: Because of the efforts of fine Americans like Frederick Douglass, countless others have seen the shining beacon of light that is education. His example was a torch that lit the way for others. Frederick Douglass was truly an American hero.
• The “Grab Bag” Conclusion. This kind of conclusion includes extra information that the writer found or thought of but couldn’t integrate into the main paper. You may find it hard to leave out details that you discovered after hours of research and thought, but adding random facts and bits of evidence at the end of an otherwise-well-organized essay can just create confusion. Example: In addition to being an educational pioneer, Frederick Douglass provides an interesting case study for masculinity in the American South. He also offers historians an interesting glimpse into slave resistance when he confronts Covey, the overseer. His relationships with female relatives reveal the importance of family in the slave community.

Works consulted

We consulted these works while writing this handout. This is not a comprehensive list of resources on the handout’s topic, and we encourage you to do your own research to find additional publications. Please do not use this list as a model for the format of your own reference list, as it may not match the citation style you are using. For guidance on formatting citations, please see the UNC Libraries citation tutorial . We revise these tips periodically and welcome feedback.

Douglass, Frederick. 1995. Narrative of the Life of Frederick Douglass, an American Slave, Written by Himself. New York: Dover.

Hamilton College. n.d. “Conclusions.” Writing Center. Accessed June 14, 2019. https://www.hamilton.edu//academics/centers/writing/writing-resources/conclusions .

Holewa, Randa. 2004. “Strategies for Writing a Conclusion.” LEO: Literacy Education Online. Last updated February 19, 2004. https://leo.stcloudstate.edu/acadwrite/conclude.html.

You may reproduce it for non-commercial use if you use the entire handout and attribute the source: The Writing Center, University of North Carolina at Chapel Hill

Make a Gift

• Link to facebook
• Link to linkedin
• Link to twitter
• Link to youtube
• Writing Tips

How to Write an Essay Conclusion

4-minute read

• 1st October 2022

Regardless of what you’re studying, writing essays is probably a significant part of your work as a student . Taking the time to understand how to write each section of an essay (i.e., introduction, body, and conclusion) can make the entire process easier and ensure that you’ll be successful.

Once you’ve put in the hard work of writing a coherent and compelling essay, it can be tempting to quickly throw together a conclusion without the same attention to detail. However, you won’t leave an impactful final impression on your readers without a strong conclusion.

We’ve compiled a few easy steps to help you write a great conclusion for your next essay . Watch our video, or check out our guide below to learn more!

1. Return to Your Thesis

Similar to how an introduction should capture your reader’s interest and present your argument, a conclusion should show why your argument matters and leave the reader with further curiosity about the topic.

To do this, you should begin by reminding the reader of your thesis statement. While you can use similar language and keywords when referring to your thesis, avoid copying it from the introduction and pasting it into your conclusion.

Try varying your vocabulary and sentence structure and presenting your thesis in a way that demonstrates how your argument has evolved throughout your essay.

2. Review Your Main Points

In addition to revisiting your thesis statement, you should review the main points you presented in your essay to support your argument.

However, a conclusion isn’t simply a summary of your essay . Rather, you should further examine your main points and demonstrate how each is connected.

Try to discuss these points concisely, in just a few sentences, in preparation for demonstrating how they fit in to the bigger picture of the topic.

Find this useful?

Subscribe to our newsletter and get writing tips from our editors straight to your inbox.

3. Show the Significance of Your Essay

Next, it’s time to think about the topic of your essay beyond the scope of your argument. It’s helpful to keep the question “so what?” in mind when you’re doing this. The goal is to demonstrate why your argument matters.

If you need some ideas about what to discuss to show the significance of your essay, consider the following:

• What do your findings contribute to the current understanding of the topic?
• Did your findings raise new questions that would benefit from future research?
• Can you offer practical suggestions for future research or make predictions about the future of the field/topic?
• Are there other contexts, topics, or a broader debate that your ideas can be applied to?

While writing your essay, it can be helpful to keep a list of ideas or insights that you develop about the implications of your work so that you can refer back to it when you write the conclusion.

Making these kinds of connections will leave a memorable impression on the reader and inspire their interest in the topic you’ve written about.

4. Avoid Some Common Mistakes

To ensure you’ve written a strong conclusion that doesn’t leave your reader confused or lacking confidence in your work, avoid:

• Presenting new evidence: Don’t introduce new information or a new argument, as it can distract from your main topic, confuse your reader, and suggest that your essay isn’t organized.
• Undermining your argument: Don’t use statements such as “I’m not an expert,” “I feel,” or “I think,” as lacking confidence in your work will weaken your argument.
• Using generic statements: Don’t use generic concluding statements such as “In summary,” “To sum up,” or “In conclusion,” which are redundant since the reader will be able to see that they’ve reached the end of your essay.

Finally, don’t make the mistake of forgetting to proofread your essay ! Mistakes can be difficult to catch in your own writing, but they can detract from your writing.

Our expert editors can ensure that your essay is clear, concise, and free of spelling and grammar errors. Find out more by submitting a free trial document today!

Share this article:

Post A New Comment

Got content that needs a quick turnaround? Let us polish your work. Explore our editorial business services.

9-minute read

How to Use Infographics to Boost Your Presentation

Is your content getting noticed? Capturing and maintaining an audience’s attention is a challenge when...

8-minute read

Why Interactive PDFs Are Better for Engagement

Are you looking to enhance engagement and captivate your audience through your professional documents? Interactive...

7-minute read

Seven Key Strategies for Voice Search Optimization

Voice search optimization is rapidly shaping the digital landscape, requiring content professionals to adapt their...

Five Creative Ways to Showcase Your Digital Portfolio

Are you a creative freelancer looking to make a lasting impression on potential clients or...

How to Ace Slack Messaging for Contractors and Freelancers

Effective professional communication is an important skill for contractors and freelancers navigating remote work environments....

3-minute read

How to Insert a Text Box in a Google Doc

Google Docs is a powerful collaborative tool, and mastering its features can significantly enhance your...

Make sure your writing is the best it can be with our expert English proofreading and editing.

• Walden University
• Faculty Portal

Writing a Paper: Conclusions

Writing a conclusion.

A conclusion is an important part of the paper; it provides closure for the reader while reminding the reader of the contents and importance of the paper. It accomplishes this by stepping back from the specifics in order to view the bigger picture of the document. In other words, it is reminding the reader of the main argument. For most course papers, it is usually one paragraph that simply and succinctly restates the main ideas and arguments, pulling everything together to help clarify the thesis of the paper. A conclusion does not introduce new ideas; instead, it should clarify the intent and importance of the paper. It can also suggest possible future research on the topic.

An Easy Checklist for Writing a Conclusion

It is important to remind the reader of the thesis of the paper so he is reminded of the argument and solutions you proposed.

Think of the main points as puzzle pieces, and the conclusion is where they all fit together to create a bigger picture. The reader should walk away with the bigger picture in mind.

Make sure that the paper places its findings in the context of real social change.

Make sure the reader has a distinct sense that the paper has come to an end. It is important to not leave the reader hanging. (You don’t want her to have flip-the-page syndrome, where the reader turns the page, expecting the paper to continue. The paper should naturally come to an end.)

No new ideas should be introduced in the conclusion. It is simply a review of the material that is already present in the paper. The only new idea would be the suggesting of a direction for future research.

Conclusion Example

As addressed in my analysis of recent research, the advantages of a later starting time for high school students significantly outweigh the disadvantages. A later starting time would allow teens more time to sleep--something that is important for their physical and mental health--and ultimately improve their academic performance and behavior. The added transportation costs that result from this change can be absorbed through energy savings. The beneficial effects on the students’ academic performance and behavior validate this decision, but its effect on student motivation is still unknown. I would encourage an in-depth look at the reactions of students to such a change. This sort of study would help determine the actual effects of a later start time on the time management and sleep habits of students.

Related Webinar

Didn't find what you need? Email us at [email protected] .

• Previous Page: Thesis Statements
• Next Page: Writer's Block
• Office of Student Disability Services

Walden Resources

Departments.

• Academic Residencies
• Academic Skills
• Career Planning and Development
• Customer Care Team
• Field Experience
• Military Services
• Student Success Advising
• Writing Skills

Centers and Offices

• Center for Social Change
• Office of Academic Support and Instructional Services
• Office of Degree Acceleration
• Office of Research and Doctoral Services
• Office of Student Affairs

Student Resources

• Doctoral Writing Assessment
• Form & Style Review
• Quick Answers
• ScholarWorks
• SKIL Courses and Workshops
• Walden Bookstore
• Walden Catalog & Student Handbook
• Student Safety/Title IX
• Legal & Consumer Information
• Website Terms and Conditions
• Cookie Policy
• Accessibility
• Accreditation
• State Authorization
• Net Price Calculator
• Contact Walden

Walden University is a member of Adtalem Global Education, Inc. www.adtalem.com Walden University is certified to operate by SCHEV © 2024 Walden University LLC. All rights reserved.

• U.S. Locations
• UMGC Europe
• Learn Online
• Find Answers
• 855-655-8682
• Current Students

Essay Conclusions

Explore more of umgc.

• Writing Resources

Contact The Effective Writing Center

E-mail:  writingcenter@umgc.edu

Learn about the elements of a successful essay conclusion.

The conclusion is a very important part of your essay. Although it is sometimes treated as a roundup of all of the bits that didn’t fit into the paper earlier, it deserves better treatment than that! It's the last thing the reader will see, so it tends to stick in the reader's memory. It's also a great place to remind the reader exactly why your topic is important. A conclusion is more than just "the last paragraph"—it's a working part of the paper. This is the place to push your reader to think about the consequences of your topic for the wider world or for the reader's own life!

A good conclusion should do a few things:

Restate your thesis

Synthesize or summarize your major points

Make the context of your argument clear

Restating Your Thesis

You've already spent time and energy crafting a solid thesis statement for your introduction, and if you've done your job right, your whole paper focuses on that thesis statement. That's why it's so important to address the thesis in your conclusion! Many writers choose to begin the conclusion by restating the thesis, but you can put your thesis into the conclusion anywhere—the first sentence of the paragraph, the last sentence, or in between. Here are a few tips for rephrasing your thesis:

Remind the reader that you've proven this thesis over the course of your paper. For example, if you're arguing that your readers should get their pets from animal shelters rather than pet stores, you might say, "If you were considering that puppy in the pet-shop window, remember that your purchase will support 'puppy mills' instead of rescuing a needy dog, and consider selecting your new friend at your local animal shelter." This example gives the reader not only the thesis of the paper, but a reminder of the most powerful point in the argument!

Revise the thesis statement so that it reflects the relationship you've developed with the reader during the paper. For example, if you've written a paper that targets parents of young children, you can find a way to phrase your thesis to capitalize on that—maybe by beginning your thesis statement with, "As a parent of a young child…"

Don’t repeat your thesis word for word—make sure that your new statement is an independent, fresh sentence!

Summary or Synthesis

This section of the conclusion might come before the thesis statement or after it. Your conclusion should remind the reader of what your paper actually says! The best conclusion will include a synthesis, not just a summary—instead of a mere list of your major points, the best conclusion will draw those points together and relate them to one another so that your reader can apply the information given in the essay. Here are a couple of ways to do that:

Give a list of the major arguments for your thesis (usually, these are the topic sentences of the parts of your essay).

Explain how these parts are connected. For example, in the animal-shelter essay, you might point out that adopting a shelter dog helps more animals because your adoption fee supports the shelter, which makes your choice more socially responsible.

One of the most important functions of the conclusion is to provide context for your argument. Your reader may finish your essay without a problem and understand your argument without understanding why that argument is important. Your introduction might point out the reason your topic matters, but your conclusion should also tackle this questions. Here are some strategies for making your reader see why the topic is important:

Tell the reader what you want him or her to do. Is your essay a call to action? If so, remind the reader of what he/she should do. If not, remember that asking the reader to think a certain way is an action in itself. (In the above examples, the essay asks the reader to adopt a shelter dog—a specific action.)

Explain why this topic is timely or important. For example, the animal-shelter essay might end with a statistic about the number of pets in shelters waiting for adoption.

Remind the readers of why the topic matters to them personally. For example, it doesn’t matter much if you believe in the mission of animal shelters, if you're not planning to get a dog; however, once you're looking for a dog, it is much more important. The conclusion of this essay might say, "Since you’re in the market for a dog, you have a major decision to make: where to get one." This will remind the reader that the argument is personally important!

Conclusion paragraphs

No cost tutoring services

Online degrees at UMGC

Our helpful admissions advisors can help you choose an academic program to fit your career goals, estimate your transfer credits, and develop a plan for your education costs that fits your budget. If you’re a current UMGC student, please visit the Help Center .

Personal Information

Contact information, additional information.

By submitting this form, you acknowledge that you intend to sign this form electronically and that your electronic signature is the equivalent of a handwritten signature, with all the same legal and binding effect. You are giving your express written consent without obligation for UMGC to contact you regarding our educational programs and services using e-mail, phone, or text, including automated technology for calls and/or texts to the mobile number(s) provided. For more details, including how to opt out, read our privacy policy or contact an admissions advisor .

Please wait, your form is being submitted.

By using our website you agree to our use of cookies. Learn more about how we use cookies by reading our  Privacy Policy .

• PRO Courses Guides New Tech Help Pro Expert Videos About wikiHow Pro Upgrade Sign In
• EDIT Edit this Article
• EXPLORE Tech Help Pro About Us Random Article Quizzes Request a New Article Community Dashboard This Or That Game Popular Categories Arts and Entertainment Artwork Books Movies Computers and Electronics Computers Phone Skills Technology Hacks Health Men's Health Mental Health Women's Health Relationships Dating Love Relationship Issues Hobbies and Crafts Crafts Drawing Games Education & Communication Communication Skills Personal Development Studying Personal Care and Style Fashion Hair Care Personal Hygiene Youth Personal Care School Stuff Dating All Categories Arts and Entertainment Finance and Business Home and Garden Relationship Quizzes Cars & Other Vehicles Food and Entertaining Personal Care and Style Sports and Fitness Computers and Electronics Health Pets and Animals Travel Education & Communication Hobbies and Crafts Philosophy and Religion Work World Family Life Holidays and Traditions Relationships Youth
• Browse Articles
• Learn Something New
• Quizzes Hot
• This Or That Game
• Train Your Brain
• Explore More
• Support wikiHow
• About wikiHow
• Log in / Sign up
• Education and Communications
• College University and Postgraduate
• Academic Writing

How to Write a Conclusion

Last Updated: July 15, 2023

Template and Sample Conclusion

This article was co-authored by Christopher Taylor, PhD and by wikiHow staff writer, Danielle Blinka, MA, MPA . Christopher Taylor is an Adjunct Assistant Professor of English at Austin Community College in Texas. He received his PhD in English Literature and Medieval Studies from the University of Texas at Austin in 2014. This article has been viewed 481,058 times.

Writing the introduction and body of a paper is a big accomplishment. Now you need to write your conclusion. Writing a conclusion can feel difficult, but it's easier if you plan ahead. First, format your conclusion by revisiting your thesis, summarizing your arguments, and making a final statement. Then, re-read and revise your conclusion to make it effective.

• Let’s say your thesis reads, “Allowing students to visit the library during lunch improves campus life and supports academic achievement because it encourages reading, allows students to start assignments early, and provides a refuge for students who eat alone.”
• You might restate it as, “Evidence shows students who have access to their school’s library during lunch check out more books and are more likely to complete their homework; additionally, students aren’t forced to eat alone.”

• You might write, “According to data, students checked out more books when they were allowed to visit their library during lunch, used that time to do research and ask for help with homework, and reported feeling less alone at lunch time. This shows that opening up the library during lunch can improve student life and academic performance."
• If you’re writing an argument essay, address the opposing argument, as well. You might write, “Although administrators worry that students will walk the halls instead of going to the library, schools that allow students into the library during lunch reported less behavioral issues during lunch than schools that don’t allow students in the library. Data show that students were spending that time checking out more books and working on homework assignments.” [3] X Trustworthy Source Purdue Online Writing Lab Trusted resource for writing and citation guidelines Go to source

• Call your reader to action . For example, “By working with school administrators, Greenlawn ISD can increase academic achievement by letting students use the library during lunch.”
• End with a warning . You might write, “If students aren’t allowed to use the library during lunch, they are missing out on a valuable learning opportunity they’ll never get back.”
• Evoke an image . Write, “Next year, students at Greenlawn could be gathered around a table in the library reading or broadening their minds.”
• Compare your topic to something universal to help your reader relate . You might write, “Everyone knows how stressful it is to have a planner full of assignments, so having extra time to work on them during lunch would be a great relief to many students.”
• Show why the issue is significant. Write, "Giving students more time to spend in the library will help them become more comfortable spending time there, which also helps the library's mission."
• Predict what would happen if your ideas are implemented . Say, “Next year, students at Greenlawn could increase their academic achievements, but results will only happen if they can use the library during lunch.”
• End with a compelling quote . For instance, "As author Roald Dahl once said, 'If you are going to get anywhere in life, you have to read a lot of books.'"

• You could also ask your instructor if you can see an example of a well-written conclusion to give you an idea about what they expect you to write.

• If you want to use an introductory phrase, use a stronger one like “based on the evidence” or “ultimately.” You might also begin your first sentence with a word like “although,” “while,” or “since.” [6] X Trustworthy Source University of North Carolina Writing Center UNC's on-campus and online instructional service that provides assistance to students, faculty, and others during the writing process Go to source
• Additionally, avoid “to conclude,” “in summary,” or “in closing.”

• For example, you may have opened your introduction with an anecdote, quote, or image. Bring it back up in your conclusion. Similarly, if you opened with a rhetorical question, you might offer a potential answer in your conclusion.

• For example, you wouldn’t want to end your essay about allowing students to use the library during lunch by stating, “As the evidence shows, using the library at lunch is a great way to improve student performance because they are more likely to do their homework. On a survey, students reported using the library to do research, ask homework questions, and finish their assignments early.” This leaves out your points about students reading more and having a place to spend their lunch period if they don’t like eating in the cafeteria.

• If you have introduced something you think is really important for your paper, go back through the body paragraphs and look for somewhere to add it. It’s better to leave it out of the paper than to include it in the conclusion.

• If something doesn’t make sense or your conclusion seems incomplete, revise your conclusion so that your ideas are clear.
• It’s helpful to read your entire paper as a whole to make sure it all comes together.

Community Q&A

• Don’t put any evidence or statistics in your conclusion. This information belongs in the body of your paper. [11] X Trustworthy Source University of North Carolina Writing Center UNC's on-campus and online instructional service that provides assistance to students, faculty, and others during the writing process Go to source Thanks Helpful 1 Not Helpful 0
• Make sure you aren’t simply repeating what you’ve written earlier. While you want to restate your ideas, present them in a new way for the reader. Thanks Helpful 0 Not Helpful 0
• Don’t write your conclusion until you’ve written the entire paper. It’ll be much easier to come up with your concluding thoughts after the body of the paper is written. Thanks Helpful 0 Not Helpful 0

• Never copy someone else’s words or ideas without giving them credit, as this is plagiarism. If you are caught plagiarizing part of your paper, even just the conclusion, you’ll likely face severe academic penalties. Thanks Helpful 5 Not Helpful 2
• Don’t express any doubts you may have about your ideas or arguments. Whenever you share your ideas, assume the role of expert. [12] X Research source Thanks Helpful 0 Not Helpful 0

You Might Also Like

• ↑ http://writing2.richmond.edu/writing/wweb/conclude.html
• ↑ https://writingcenter.unc.edu/tips-and-tools/conclusions/
• ↑ https://owl.purdue.edu/owl/general_writing/common_writing_assignments/argument_papers/conclusions.html
• ↑ https://writingcenter.fas.harvard.edu/pages/ending-essay-conclusions

About This Article

Writing a conclusion can seem difficult, but it’s easier if you think of it as a place to sum up the point of your paper. Begin your conclusion by restating your thesis, but don’t repeat it word-for-word. Then, use 1-2 sentences to summarize your argument, pulling together all of your points to explain how your evidence supports the thesis. End the paper with a statement that makes the reader think, like evoking a strong image or concluding with a call to action. Keep reading for tips on how to avoid cliches in your conclusion! Did this summary help you? Yes No

• Send fan mail to authors

Reader Success Stories

Pragya Kujur

Sep 26, 2020

Did this article help you?

Anne Chinasa

Aug 28, 2020

Gregh Alcomendras

Oct 18, 2017

Ivanice Bido

Dec 10, 2017

Jun 19, 2017

Featured Articles

Trending Articles

Watch Articles

• Terms of Use
• Privacy Policy
• Do Not Sell or Share My Info
• Not Selling Info

Don’t miss out! Sign up for

wikiHow’s newsletter

Get science-backed answers as you write with Paperpal's Research feature

How to Write a Conclusion for Research Papers (with Examples)

The conclusion of a research paper is a crucial section that plays a significant role in the overall impact and effectiveness of your research paper. However, this is also the section that typically receives less attention compared to the introduction and the body of the paper. The conclusion serves to provide a concise summary of the key findings, their significance, their implications, and a sense of closure to the study. Discussing how can the findings be applied in real-world scenarios or inform policy, practice, or decision-making is especially valuable to practitioners and policymakers. The research paper conclusion also provides researchers with clear insights and valuable information for their own work, which they can then build on and contribute to the advancement of knowledge in the field.

The research paper conclusion should explain the significance of your findings within the broader context of your field. It restates how your results contribute to the existing body of knowledge and whether they confirm or challenge existing theories or hypotheses. Also, by identifying unanswered questions or areas requiring further investigation, your awareness of the broader research landscape can be demonstrated.

Remember to tailor the research paper conclusion to the specific needs and interests of your intended audience, which may include researchers, practitioners, policymakers, or a combination of these.

Table of Contents

What is a conclusion in a research paper, summarizing conclusion, editorial conclusion, externalizing conclusion, importance of a good research paper conclusion, how to write a conclusion for your research paper, research paper conclusion examples.

• How to write a research paper conclusion with Paperpal? 

Frequently Asked Questions

A conclusion in a research paper is the final section where you summarize and wrap up your research, presenting the key findings and insights derived from your study. The research paper conclusion is not the place to introduce new information or data that was not discussed in the main body of the paper. When working on how to conclude a research paper, remember to stick to summarizing and interpreting existing content. The research paper conclusion serves the following purposes: 1

• Warn readers of the possible consequences of not attending to the problem.
• Recommend specific course(s) of action.
• Restate key ideas to drive home the ultimate point of your research paper.
• Provide a “take-home” message that you want the readers to remember about your study.

Types of conclusions for research papers

In research papers, the conclusion provides closure to the reader. The type of research paper conclusion you choose depends on the nature of your study, your goals, and your target audience. I provide you with three common types of conclusions:

A summarizing conclusion is the most common type of conclusion in research papers. It involves summarizing the main points, reiterating the research question, and restating the significance of the findings. This common type of research paper conclusion is used across different disciplines.

An editorial conclusion is less common but can be used in research papers that are focused on proposing or advocating for a particular viewpoint or policy. It involves presenting a strong editorial or opinion based on the research findings and offering recommendations or calls to action.

An externalizing conclusion is a type of conclusion that extends the research beyond the scope of the paper by suggesting potential future research directions or discussing the broader implications of the findings. This type of conclusion is often used in more theoretical or exploratory research papers.

Align your conclusion’s tone with the rest of your research paper. Start Writing with Paperpal Now!  

The conclusion in a research paper serves several important purposes:

• Offers Implications and Recommendations : Your research paper conclusion is an excellent place to discuss the broader implications of your research and suggest potential areas for further study. It’s also an opportunity to offer practical recommendations based on your findings.
• Provides Closure : A good research paper conclusion provides a sense of closure to your paper. It should leave the reader with a feeling that they have reached the end of a well-structured and thought-provoking research project.
• Leaves a Lasting Impression : Writing a well-crafted research paper conclusion leaves a lasting impression on your readers. It’s your final opportunity to leave them with a new idea, a call to action, or a memorable quote.

Writing a strong conclusion for your research paper is essential to leave a lasting impression on your readers. Here’s a step-by-step process to help you create and know what to put in the conclusion of a research paper: 2

• Research Statement : Begin your research paper conclusion by restating your research statement. This reminds the reader of the main point you’ve been trying to prove throughout your paper. Keep it concise and clear.
• Key Points : Summarize the main arguments and key points you’ve made in your paper. Avoid introducing new information in the research paper conclusion. Instead, provide a concise overview of what you’ve discussed in the body of your paper.
• Address the Research Questions : If your research paper is based on specific research questions or hypotheses, briefly address whether you’ve answered them or achieved your research goals. Discuss the significance of your findings in this context.
• Significance : Highlight the importance of your research and its relevance in the broader context. Explain why your findings matter and how they contribute to the existing knowledge in your field.
• Implications : Explore the practical or theoretical implications of your research. How might your findings impact future research, policy, or real-world applications? Consider the “so what?” question.
• Future Research : Offer suggestions for future research in your area. What questions or aspects remain unanswered or warrant further investigation? This shows that your work opens the door for future exploration.
• Closing Thought : Conclude your research paper conclusion with a thought-provoking or memorable statement. This can leave a lasting impression on your readers and wrap up your paper effectively. Avoid introducing new information or arguments here.
• Proofread and Revise : Carefully proofread your conclusion for grammar, spelling, and clarity. Ensure that your ideas flow smoothly and that your conclusion is coherent and well-structured.

Write your research paper conclusion 2x faster with Paperpal. Try it now!

Remember that a well-crafted research paper conclusion is a reflection of the strength of your research and your ability to communicate its significance effectively. It should leave a lasting impression on your readers and tie together all the threads of your paper. Now you know how to start the conclusion of a research paper and what elements to include to make it impactful, let’s look at a research paper conclusion sample.

How to write a research paper conclusion with Paperpal?

A research paper conclusion is not just a summary of your study, but a synthesis of the key findings that ties the research together and places it in a broader context. A research paper conclusion should be concise, typically around one paragraph in length. However, some complex topics may require a longer conclusion to ensure the reader is left with a clear understanding of the study’s significance. Paperpal, an AI writing assistant trusted by over 800,000 academics globally, can help you write a well-structured conclusion for your research paper. 

• Sign Up or Log In: Create a new Paperpal account or login with your details.  
• Navigate to Features : Once logged in, head over to the features’ side navigation pane. Click on Templates and you’ll find a suite of generative AI features to help you write better, faster.  
• Generate an outline: Under Templates, select ‘Outlines’. Choose ‘Research article’ as your document type.  
• Select your section: Since you’re focusing on the conclusion, select this section when prompted.  
• Choose your field of study: Identifying your field of study allows Paperpal to provide more targeted suggestions, ensuring the relevance of your conclusion to your specific area of research. 
• Provide a brief description of your study: Enter details about your research topic and findings. This information helps Paperpal generate a tailored outline that aligns with your paper’s content. 
• Generate the conclusion outline: After entering all necessary details, click on ‘generate’. Paperpal will then create a structured outline for your conclusion, to help you start writing and build upon the outline.  
• Write your conclusion: Use the generated outline to build your conclusion. The outline serves as a guide, ensuring you cover all critical aspects of a strong conclusion, from summarizing key findings to highlighting the research’s implications. 
• Refine and enhance: Paperpal’s ‘Make Academic’ feature can be particularly useful in the final stages. Select any paragraph of your conclusion and use this feature to elevate the academic tone, ensuring your writing is aligned to the academic journal standards. 

By following these steps, Paperpal not only simplifies the process of writing a research paper conclusion but also ensures it is impactful, concise, and aligned with academic standards. Sign up with Paperpal today and write your research paper conclusion 2x faster .  

The research paper conclusion is a crucial part of your paper as it provides the final opportunity to leave a strong impression on your readers. In the research paper conclusion, summarize the main points of your research paper by restating your research statement, highlighting the most important findings, addressing the research questions or objectives, explaining the broader context of the study, discussing the significance of your findings, providing recommendations if applicable, and emphasizing the takeaway message. The main purpose of the conclusion is to remind the reader of the main point or argument of your paper and to provide a clear and concise summary of the key findings and their implications. All these elements should feature on your list of what to put in the conclusion of a research paper to create a strong final statement for your work.

A strong conclusion is a critical component of a research paper, as it provides an opportunity to wrap up your arguments, reiterate your main points, and leave a lasting impression on your readers. Here are the key elements of a strong research paper conclusion: 1. Conciseness : A research paper conclusion should be concise and to the point. It should not introduce new information or ideas that were not discussed in the body of the paper. 2. Summarization : The research paper conclusion should be comprehensive enough to give the reader a clear understanding of the research’s main contributions. 3 . Relevance : Ensure that the information included in the research paper conclusion is directly relevant to the research paper’s main topic and objectives; avoid unnecessary details. 4 . Connection to the Introduction : A well-structured research paper conclusion often revisits the key points made in the introduction and shows how the research has addressed the initial questions or objectives. 5. Emphasis : Highlight the significance and implications of your research. Why is your study important? What are the broader implications or applications of your findings? 6 . Call to Action : Include a call to action or a recommendation for future research or action based on your findings.

The length of a research paper conclusion can vary depending on several factors, including the overall length of the paper, the complexity of the research, and the specific journal requirements. While there is no strict rule for the length of a conclusion, but it’s generally advisable to keep it relatively short. A typical research paper conclusion might be around 5-10% of the paper’s total length. For example, if your paper is 10 pages long, the conclusion might be roughly half a page to one page in length.

In general, you do not need to include citations in the research paper conclusion. Citations are typically reserved for the body of the paper to support your arguments and provide evidence for your claims. However, there may be some exceptions to this rule: 1. If you are drawing a direct quote or paraphrasing a specific source in your research paper conclusion, you should include a citation to give proper credit to the original author. 2. If your conclusion refers to or discusses specific research, data, or sources that are crucial to the overall argument, citations can be included to reinforce your conclusion’s validity.

The conclusion of a research paper serves several important purposes: 1. Summarize the Key Points 2. Reinforce the Main Argument 3. Provide Closure 4. Offer Insights or Implications 5. Engage the Reader. 6. Reflect on Limitations

Remember that the primary purpose of the research paper conclusion is to leave a lasting impression on the reader, reinforcing the key points and providing closure to your research. It’s often the last part of the paper that the reader will see, so it should be strong and well-crafted.

• Makar, G., Foltz, C., Lendner, M., & Vaccaro, A. R. (2018). How to write effective discussion and conclusion sections. Clinical spine surgery, 31(8), 345-346.
• Bunton, D. (2005). The structure of PhD conclusion chapters.  Journal of English for academic purposes ,  4 (3), 207-224.

Paperpal is a comprehensive AI writing toolkit that helps students and researchers achieve 2x the writing in half the time. It leverages 21+ years of STM experience and insights from millions of research articles to provide in-depth academic writing, language editing, and submission readiness support to help you write better, faster.  

Get accurate academic translations, rewriting support, grammar checks, vocabulary suggestions, and generative AI assistance that delivers human precision at machine speed. Try for free or upgrade to Paperpal Prime starting at US$19 a month to access premium features, including consistency, plagiarism, and 30+ submission readiness checks to help you succeed.  

Experience the future of academic writing – Sign up to Paperpal and start writing for free!  

Related Reads:

• 5 Reasons for Rejection After Peer Review
• Ethical Research Practices For Research with Human Subjects

7 Ways to Improve Your Academic Writing Process

• Paraphrasing in Academic Writing: Answering Top Author Queries

Preflight For Editorial Desk: The Perfect Hybrid (AI + Human) Assistance Against Compromised Manuscripts

You may also like, how to write the first draft of a..., mla works cited page: format, template & examples, how to write a high-quality conference paper, academic editing: how to self-edit academic text with..., measuring academic success: definition & strategies for excellence, phd qualifying exam: tips for success , ai in education: it’s time to change the..., is it ethical to use ai-generated abstracts without..., what are journal guidelines on using generative ai..., quillbot review: features, pricing, and free alternatives.

More From Forbes

5 strategies to unlock your winning college essay.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

CAMBRIDGE, MASSACHUSETTS - JUNE 29: People walk through the gate on Harvard Yard at the Harvard ... [+] University campus on June 29, 2023 in Cambridge, Massachusetts. The U.S. Supreme Court ruled that race-conscious admission policies used by Harvard and the University of North Carolina violate the Constitution, bringing an end to affirmative action in higher education. (Photo by Scott Eisen/Getty Images)

The college application season is upon us, and high school students everywhere are staring down at one of the most daunting tasks: the college essay. As someone who has guided countless applicants through the admissions process and reviewed admissions essays on an undergraduate admissions committee, I've pinpointed the essential ingredient to a differentiated candidacy—the core of your college admissions X-factor .

The essential ingredient to your college admissions X-factor is your intellectual vitality. Intellectual vitality is your passion for learning and curiosity. By demonstrating and conveying this passion, you can transform an average essay into a compelling narrative that boosts your chances of getting accepted to your top schools. Here are five dynamic strategies to achieve that goal.

Unleash Your Authentic Voice

Admissions officers sift through thousands of essays every year. What stops them in their tracks? An authentic voice that leaps off the page. Forget trying to guess what the admissions committee wants to hear. Focus on being true to yourself. Share your unique perspective, your passions, and your values. Authenticity resonates deeply with application reviewers, making your essay memorable and impactful. You need not have experienced trauma or tragedy to create a strong narrative. You can write about what you know—intellectually or personally—to convey your enthusiasm, creativity, and leadership. Intellectual vitality shines through when you write with personalized reflection about what lights you up.

Weave A Captivating Story

Everyone loves a good story, and your essay is the perfect place to tell yours. The Common Application personal statement has seven choices of prompts to ground the structure for your narrative. The most compelling stories are often about the smallest moments in life, whether it’s shopping at Costco or about why you wear socks that have holes. Think of the Common Application personal statement as a window into your soul rather than a dry list of your achievements or your overly broad event-based life story. Use vivid anecdotes to bring your experiences to life. A well-told story can showcase your growth, highlight your character, and illustrate how you've overcome challenges. Intellectual vitality often emerges in these narratives, revealing how your curiosity and proactive approach to learning have driven you to explore and innovate.

Reflect And Reveal Insights

It's not just about what you've done—it's about what you've learned along the way. When you are writing about a specific event, you can use the STAR framework—situation, task, action, and result (your learning). Focus most of your writing space on the “R” part of this framework to dive deeply into your experiences and reflect on how they've shaped your aspirations and identity.

Google Chrome Deadline—72 Hours To Update Or Delete Your Browser

The fed quietly admits gold is replacing the dollar as collapse fear predicted to trigger a 15 7 trillion etf bitcoin price flip, apple loop iphone 16 pro details ios 18 s ai plans iphone 14 pro special offer.

The most insightful college-specific supplement essays demonstrate depth of thought, and the ability to connect past experiences with your future life in college and beyond. Reflecting on your intellectual journey signals maturity and a readiness to embrace the college experience. It shows admissions officers that you engage deeply with your studies and are eager to contribute to the academic community.

Highlight Your Contributions—But Don’t Brag

Whether it's a special talent, an unusual hobby, or a unique perspective, showcasing what you can bring to the college environment can make a significant impact. Recognize that the hard work behind the accomplishment is what colleges are interested in learning more about—not retelling about the accomplishment itself. (Honors and activities can be conveyed in another section of the application.) Walk us through the journey to your summit; don’t just take us to the peak and expect us know how you earned it.

Intellectual vitality can be demonstrated through your proactive approach to solving problems, starting new projects, or leading initiatives that reflect your passion for learning and growth. These experiences often have a place in the college-specific supplement essays. They ground the reasons why you want to study in your major and at the particular college.

Perfect Your Prose

Great writing is essential. Anyone can use AI or a thesaurus to assist with an essay, but AI cannot write your story in the way that you tell it. Admissions officers don’t give out extra credit for choosing the longest words with the most amount of syllables.

The best essays have clear, coherent language and are free of errors. The story is clearly and specifically told. After drafting, take the time to revise and polish your writing. Seek feedback from teachers, mentors, or trusted friends, but ensure the final piece is unmistakably yours. A well-crafted essay showcases your diligence and attention to detail—qualities that admissions officers highly value. Intellectual vitality is also reflected in your writing process, showing your commitment to excellence and your enthusiasm for presenting your best self.

Crafting a standout college essay is about presenting your true self in an engaging, reflective, and polished manner while showcasing your intellectual vitality. Happy writing.

• Editorial Standards
• Reprints & Permissions

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Welcome to the Purdue Online Writing Lab

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

The Online Writing Lab at Purdue University houses writing resources and instructional material, and we provide these as a free service of the Writing Lab at Purdue. Students, members of the community, and users worldwide will find information to assist with many writing projects. Teachers and trainers may use this material for in-class and out-of-class instruction.

The Purdue On-Campus Writing Lab and Purdue Online Writing Lab assist clients in their development as writers—no matter what their skill level—with on-campus consultations, online participation, and community engagement. The Purdue Writing Lab serves the Purdue, West Lafayette, campus and coordinates with local literacy initiatives. The Purdue OWL offers global support through online reference materials and services.

A Message From the Assistant Director of Content Development 

The Purdue OWL® is committed to supporting  students, instructors, and writers by offering a wide range of resources that are developed and revised with them in mind. To do this, the OWL team is always exploring possibilties for a better design, allowing accessibility and user experience to guide our process. As the OWL undergoes some changes, we welcome your feedback and suggestions by email at any time.

Please don't hesitate to contact us via our contact page  if you have any questions or comments.

All the best,

Social Media

Facebook twitter.

Secondary Medical School Application Essays: How to Shine

Emphasizing fit and showing authenticity help medical school secondary essays stand out, experts say.

Tips for Secondary Med School Essays

Getty Images | iStockphoto

One of best pieces of advice when writing an application essay is to be authentic.

Key Takeaways

• Secondary medical school essays should highlight why an applicant is a good fit.
• Applicants should submit the essays early without compromising quality.
• It's important to be authentic in essay responses.

After receiving primary applications, most medical schools ask applicants to complete a secondary application, which typically includes additional essay questions. While primary essay prompts ask why you're pursuing medicine, medical school secondary essays focus on you and how you fit with a specific school.

Secondary essay prompts vary by school, but they're generally designed to help med schools learn about you at a deeper level. They may ask you to reflect on what makes you who you are, a time when you worked with a population different than yourself, an occasion where you asked for help or a time when you worked in a team. They may ask how you spent a gap year before applying to medical school or what you did after your undergraduate degree.

"What we are trying to figure out is if this is a candidate that can fulfill the premedical competencies and whether they are mission-aligned," says Dr. Wendy Jackson, associate dean for admissions at the University of Kentucky College of Medicine . “Can they help fulfill the needs that our institution is trying to deliver?”

A lot rides on these essays, but keeping a few best practices in mind can make the process less daunting.

Emphasize Fit

The first thing medical schools look for is whether an applicant will be a good fit for the school’s mission, Jackson says.

“I would challenge someone who is completing a secondary application to understand the mission of the school and envision how they are going to contribute to that,” she says. “The vast majority of schools are going to ask why you chose their institution, so you need to be prepared to answer that.”

Some secondary essay questions are optional, but experts recommend answering them even though they're extra work. For example, the Vanderbilt University School of Medicine in Tennessee asks applicants what makes them interested in the school.

“We just want to see if they’re a good fit for us and that they’ve done a little bit of homework about Vanderbilt," says Jennifer Kimble, director of admissions at Vanderbilt's medical school. "We want to make sure that the students we admit are going to be happy with their Vanderbilt experience.”

Avoid focusing on what you’re going to gain from the school – schools are really asking how you'll be an asset to the program.

"It’s almost like if you’re trying to date someone and you tell them, ‘Here’s what I’m going to get from this relationship,’ without saying, ‘We’re better off together,’” says Shirag Shemmassian, founder of Shemmassian Academic Consulting. “You have to sell the idea that you’re bettering one another and how you’re better together than apart. I think students often miss that latter component."

Don't Procrastinate

The medical school application process is often compared to a marathon, but the final steps may feel like a sprint. Applicants typically receive secondary application requests in late June, and in some cases schools want those back within a matter of weeks. Others set deadlines months down the road.

Either way, because of rolling admissions , it's best to send essays in as early as possible without compromising quality, Shemmassian says.

The earlier an applicant submits materials, the less competition they typically face, experts say. For example, Vanderbilt receives nearly 7,000 applications per year. Of those, roughly 600 applicants will be asked to interview and around 260 will be offered admission for 96 spots.

"At the beginning of the cycle, our calendar is wide open and we’re very open to who we bring in for an interview," Kimble says. "Down the road when we only have 30 seats left, it’s highly selective who those candidates are that get those coveted 30 interview spots that are left over."

Prewrite Essays

Applicants won't know the specific language of secondary essay prompts until schools send them, but in many cases, essay prompts are similar year to year and the previous year's prompts are often published on a school's admissions website, experts say. Some schools may change or tweak questions, but you can generally get a head start by prewriting essays based on previous prompts.

"As the new ones come out, you can modify as needed," Shemmassian says. "I would say that about 70% to 80% of prompts will remain the same or similar. If they change, you can usually adapt an essay you’ve written for another school."

Secondary essays vary in length and number. Vanderbilt requires applicants to submit an 800-word essay and two 600-word essays. Some schools may require close to 10 secondary essays. Shemmassian says this is significantly more writing than applicants are used to, so budgeting time is crucial.

But applicants should take care when prewriting essays and make sure each is tailored to the specific school with the correct school name, experts say. Jackson says she's read plenty of essays where applicants included the wrong school name and it cost them.

“You may think you can save time by cutting and pasting or taking half of a previously written essay response and making a modification,” Jackson says. “Be careful, because the questions vary from institution to institution.”

Experts say applicants often neglect to fully read prompts in their haste to complete answers. Though there's a time crunch, it's vital to thoroughly read the prompt and answer the question fully without grammatical or spelling errors.

“That seems kind of silly, but I think we can get going down a road when we’re writing and feel like we’ve completed and written something well but look back and never really have a response to the true question being asked," Jackson says.

Be Authentic

Medical school applicants tend to put a lot of pressure on themselves to write something that schools haven't read before, Kimble says. Given that med schools sift through thousands of applicants a year, "we’ve read all sorts of scenarios in life, so take that pressure and put it on the shelf," she says. "That’s not a concern for us. We aren’t looking for something that’s totally innovative."

Experts say schools are mostly looking for authenticity and an organic, genuine tone. The tone "can make or break an applicant," Jackson says.

It may be tempting, especially given time constraints, to rely on outside help – such as ChatGPT or other AI-powered software – to write essays. While some professors and admissions officers have embraced AI to help automate certain processes, Kimble says she strongly discourages med school applicants from using AI to help with secondary essays.

"We had an (application) that you could clearly see was not written by a human voice," she says. "It sounded very computer generated, so we ended up passing on the candidate just because we want to hear their story in their own words."

A Secondary Essay Example

Shemmassian compiles more than 1,000 sample secondary essays each year, using prompts from more than 150 medical schools in various states, and offers them to paying clients. The excerpted example below, created by Shemmassian's team and used with their permission, shows what he considers to be a successful diversity-themed essay in response to a Yale University School of Medicine prompt that asks applicants to reflect on how their background and experiences contribute to the school's focus on diversity and how it will inform their future role as a doctor.

As a child, one of my favorite times of the year was the summer, when I would travel to Yemen… at least until I turned twelve. Suddenly, the traditional and, in my Yemeni American view, restrictive laws for women, applied to me. Perhaps the most representative of these laws was having to cover my hair with a scarf-like garment. Staying true to my values, I decided against returning to Yemen, thereby losing a vital connection to my culture. However, this estrangement did not inhibit my growth.

The 500-word response continues with how the applicant met a Yemeni student who grew up in France and was barred from wearing a headscarf due to a school uniform policy. Where the applicant saw the headscarf as restrictive, the other student saw it as a connection to her roots. The applicant describes how although the same object held different meanings to two people from the same background, she used that to appreciate different perspectives and to advocate for a woman's right to express herself.

Later that year, I applied this lesson in perspective to my work as a clinical coordinator, when a patient walked into the office and handed me a piece of paper explaining she only spoke Arabic...By thinking critically while vernacularly translating the doctor’s advice, I was directly involved in the process of her medical care. Because of my experience in exploring the multi-cultural barriers I faced alongside the Yemeni French student who cherished her headscarf, I spent time talking to this Yemeni patient about the barriers she had faced in receiving care.

This experience motivated me to help overcome cultural healthcare barriers and disparities, showcasing my devotion to equitable treatment by creating a new protocol within the clinic where I work. Now, when scheduling patients over the phone, we ask if they have any language preferences, and we have a series of scripts we can use during each patient’s treatment.

The applicant then drives home why she believes she's a good fit for the school.

My background and experiences will contribute to Yale School of Medicine’s diversity and inform my future role as a physician by creating a student organization that holds informational workshops, utilizing my unique experiences to connect with Yale’s diverse patient population, and working to address healthcare disparities as a future physician. I envision these informational workshops would operate in the Haven Free Clinic patient waiting rooms to empower all patients, regardless of their background.

This essay is successful because it does more than tell essay readers about the applicant's background, Shemmassian says. It shows how the applicant grew "into a more compassionate and culturally humble future physician who will help patients overcome health care barriers."

"Strong diversity essays will always show admissions committees how a unique trait or life experience will help them become a better physician," he says. "This essay is especially successful because the applicant connects their experiences and what they’ve learned because of them to the Yale School of Medicine itself. This is an applicant who is already thinking deeply about not just what they can get out of medical school but how they can contribute to the values and mission of the school they attend."

Searching for a medical school? Get our  complete rankings  of Best Medical Schools.

Medical School Application Mistakes

Tags: medical school , doctors , graduate schools , education , students

You May Also Like

15 b-schools with low acceptance rates.

Ilana Kowarski and Cole Claybourn June 5, 2024

Advice About Online J.D. Programs

Gabriel Kuris June 3, 2024

Questions to Ask Ahead of Law School

Cole Claybourn May 31, 2024

Ways Women Can Thrive in B-School

Anayat Durrani May 29, 2024

Study Away or Abroad in Law School

Gabriel Kuris May 28, 2024

A Guide to Executive MBA Degrees

Ilana Kowarski and Cole Claybourn May 24, 2024

How to Choose a Civil Rights Law School

Anayat Durrani May 22, 2024

Avoid Procrastinating in Medical School

Kathleen Franco, M.D., M.S. May 21, 2024

Good Law School Recommendation Letters

Gabriel Kuris May 20, 2024

Get Accepted to Multiple Top B-schools

Anayat Durrani May 16, 2024

A charming look at a reader’s many moods

Elisa Gabbert’s essays in “Any Person Is the Only Self” are brimming with pleasure and curiosity about a life with books.

Tell people you read and write for a living, and they picture a ghostly creature, an idea only incidentally appended to a body. What they often fail to understand is that the life of the mind is also a physical life — a life spent lugging irksomely heavy volumes around on the Metro and annotating their margins with a cramping hand. The poet, essayist and New York Times poetry columnist Elisa Gabbert is rare in grasping that reading is, in addition to a mental exercise, a movement performed in a particular place.

“If I remember anything about a book, I also remember where I read it — what room, what chair,” she writes in her charming new essay collection, “ Any Person Is the Only Self .” Writing, too, proves spatial: “I think essays, like buildings, need structure and mood. The first paragraph should function as a foyer or an antechamber, bringing you into the mood.”

The 16 delightfully digressive pieces in this collection are all moods that involve books in one way or another. But they are not just about the content of books, although they are about that, too: They are primarily about the acts of reading and writing, which are as much social and corporeal as cerebral.

In the first essay — the foyer — Gabbert writes about the shelf of newly returned books at her local library. “The books on that shelf weren’t being marketed to me,” she writes. “They weren’t omnipresent in my social media feeds. They were very often old and very often ugly. I came to think of that shelf as an escape from hype.” The haphazard selections on the shelf were also evidence of other people — the sort of invisible but palpable community of readers that she came to miss so sharply during the pandemic.

In another essay, she learns of a previously unpublished story by one of her favorite authors, Sylvia Plath, who makes frequent appearances throughout this book. Fearing that the story will disappoint her, Gabbert puts off reading it. As she waits, she grows “apprehensive, even frightened.”

There are writers who attempt to excise themselves from their writing, to foster an illusion of objectivity; thankfully, Gabbert is not one of them. On the contrary, her writing is full of intimacies, and her book is a work of embodied and experiential criticism, a record of its author’s shifting relationships with the literature that defines her life. In one piece, she rereads and reappraises books she first read as a teenager; in another, she and her friends form a “Stupid Classics Book Club,” to tackle “all the corny stuff from the canon that we really should have read in school but never had.”

Gabbert is a master of mood, not polemic, and accordingly, her writing is not didactic; her essays revolve around images and recollections rather than arguments. In place of the analytic pleasures of a robustly defended thesis, we find the fresh thrills of a poet’s perfected phrases and startling observations. “Parties are about the collective gaze, the ability to be seen from all angles, panoramically,” she writes in an essay about fictional depictions of parties. She describes the photos in a book by Rachael Ray documenting home-cooked meals — one of the volumes on the recently returned shelf — as “poignantly mediocre.” Remarking on a listicle of “Books to Read by Living Women (Instead of These 10 by Dead Men),” Gabbert wonders, “Since when is it poor form to die?”

“Any Person Is the Only Self” is both funny and serious, a winning melee of high and low cultural references, as packed with unexpected treasures as a crowded antique shop. An academic text on architecture, the Austrian poet Rainer Maria Rilke, a rare memory disorder whose victims recall every aspect of their autobiographies in excruciatingly minute detail, “Madame Bovary,” YouTube videos about people who work as professional cuddlers, a psychological study about whether it is possible to be sane in an insane asylum — all these feature in Gabbert’s exuberant essays. She is a fiercely democratic thinker, incapable of snobbery and brimming with curiosity.

Perhaps because she is so indefatigably interested, she gravitates toward writers who see literature as a means of doubling life, allowing it to hold twice as much. Plath confessed in her journals that she wrote in an attempt to extend her biography beyond its biological terminus: “My life, I feel, will not be lived until there are books and stories which relive it perpetually in time.” The very act of keeping a diary, then, splits the self in two.

Plath once insisted that bad things could never happen to her and her peers because “we’re different.” Gabbert asks “Different why?” and concludes that everyone is different: “We are we , not them. Any person is the only self.” But that “only” is, perhaps counterintuitively, not constrained or constricted. Walt Whitman famously wrote that his only self comprised “multitudes,” and Gabbert echoes him when she reflects, “If there is no one self, you can never be yourself, only one of your selves.” And indeed, she is loath to elevate any of her many selves over any of the others. When she rereads a book that she loved in her adolescence, she thinks she was right to love it back then. “That self only knew what she knew,” she writes. “That self wasn’t wrong .” Both her past self and her present self have an equal claim to being Elisa Gabbert, who is too fascinated by the world’s manifold riches to confine herself to a single, limited life.

Becca Rothfeld is the nonfiction book critic for The Washington Post and the author of “All Things Are Too Small: Essays in Praise of Excess.”

Any Person Is the Only Self

By Elisa Gabbert

FSG Originals. 230 pp. $18, paperback.

We are a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 03 June 2024

Applying large language models for automated essay scoring for non-native Japanese

• Wenchao Li 1 &
• Haitao Liu 2  

Humanities and Social Sciences Communications volume  11 , Article number:  723 ( 2024 ) Cite this article

12 Accesses

1 Altmetric

Metrics details

• Language and linguistics

Recent advancements in artificial intelligence (AI) have led to an increased use of large language models (LLMs) for language assessment tasks such as automated essay scoring (AES), automated listening tests, and automated oral proficiency assessments. The application of LLMs for AES in the context of non-native Japanese, however, remains limited. This study explores the potential of LLM-based AES by comparing the efficiency of different models, i.e. two conventional machine training technology-based methods (Jess and JWriter), two LLMs (GPT and BERT), and one Japanese local LLM (Open-Calm large model). To conduct the evaluation, a dataset consisting of 1400 story-writing scripts authored by learners with 12 different first languages was used. Statistical analysis revealed that GPT-4 outperforms Jess and JWriter, BERT, and the Japanese language-specific trained Open-Calm large model in terms of annotation accuracy and predicting learning levels. Furthermore, by comparing 18 different models that utilize various prompts, the study emphasized the significance of prompts in achieving accurate and reliable evaluations using LLMs.

Similar content being viewed by others

Scoring method of English composition integrating deep learning in higher vocational colleges

ChatGPT-3.5 as writing assistance in students’ essays

Detecting contract cheating through linguistic fingerprint

Conventional machine learning technology in aes.

AES has experienced significant growth with the advancement of machine learning technologies in recent decades. In the earlier stages of AES development, conventional machine learning-based approaches were commonly used. These approaches involved the following procedures: a) feeding the machine with a dataset. In this step, a dataset of essays is provided to the machine learning system. The dataset serves as the basis for training the model and establishing patterns and correlations between linguistic features and human ratings. b) the machine learning model is trained using linguistic features that best represent human ratings and can effectively discriminate learners’ writing proficiency. These features include lexical richness (Lu, 2012 ; Kyle and Crossley, 2015 ; Kyle et al. 2021 ), syntactic complexity (Lu, 2010 ; Liu, 2008 ), text cohesion (Crossley and McNamara, 2016 ), and among others. Conventional machine learning approaches in AES require human intervention, such as manual correction and annotation of essays. This human involvement was necessary to create a labeled dataset for training the model. Several AES systems have been developed using conventional machine learning technologies. These include the Intelligent Essay Assessor (Landauer et al. 2003 ), the e-rater engine by Educational Testing Service (Attali and Burstein, 2006 ; Burstein, 2003 ), MyAccess with the InterlliMetric scoring engine by Vantage Learning (Elliot, 2003 ), and the Bayesian Essay Test Scoring system (Rudner and Liang, 2002 ). These systems have played a significant role in automating the essay scoring process and providing quick and consistent feedback to learners. However, as touched upon earlier, conventional machine learning approaches rely on predetermined linguistic features and often require manual intervention, making them less flexible and potentially limiting their generalizability to different contexts.

In the context of the Japanese language, conventional machine learning-incorporated AES tools include Jess (Ishioka and Kameda, 2006 ) and JWriter (Lee and Hasebe, 2017 ). Jess assesses essays by deducting points from the perfect score, utilizing the Mainichi Daily News newspaper as a database. The evaluation criteria employed by Jess encompass various aspects, such as rhetorical elements (e.g., reading comprehension, vocabulary diversity, percentage of complex words, and percentage of passive sentences), organizational structures (e.g., forward and reverse connection structures), and content analysis (e.g., latent semantic indexing). JWriter employs linear regression analysis to assign weights to various measurement indices, such as average sentence length and total number of characters. These weights are then combined to derive the overall score. A pilot study involving the Jess model was conducted on 1320 essays at different proficiency levels, including primary, intermediate, and advanced. However, the results indicated that the Jess model failed to significantly distinguish between these essay levels. Out of the 16 measures used, four measures, namely median sentence length, median clause length, median number of phrases, and maximum number of phrases, did not show statistically significant differences between the levels. Additionally, two measures exhibited between-level differences but lacked linear progression: the number of attributives declined words and the Kanji/kana ratio. On the other hand, the remaining measures, including maximum sentence length, maximum clause length, number of attributive conjugated words, maximum number of consecutive infinitive forms, maximum number of conjunctive-particle clauses, k characteristic value, percentage of big words, and percentage of passive sentences, demonstrated statistically significant between-level differences and displayed linear progression.

Both Jess and JWriter exhibit notable limitations, including the manual selection of feature parameters and weights, which can introduce biases into the scoring process. The reliance on human annotators to label non-native language essays also introduces potential noise and variability in the scoring. Furthermore, an important concern is the possibility of system manipulation and cheating by learners who are aware of the regression equation utilized by the models (Hirao et al. 2020 ). These limitations emphasize the need for further advancements in AES systems to address these challenges.

Deep learning technology in AES

Deep learning has emerged as one of the approaches for improving the accuracy and effectiveness of AES. Deep learning-based AES methods utilize artificial neural networks that mimic the human brain’s functioning through layered algorithms and computational units. Unlike conventional machine learning, deep learning autonomously learns from the environment and past errors without human intervention. This enables deep learning models to establish nonlinear correlations, resulting in higher accuracy. Recent advancements in deep learning have led to the development of transformers, which are particularly effective in learning text representations. Noteworthy examples include bidirectional encoder representations from transformers (BERT) (Devlin et al. 2019 ) and the generative pretrained transformer (GPT) (OpenAI).

BERT is a linguistic representation model that utilizes a transformer architecture and is trained on two tasks: masked linguistic modeling and next-sentence prediction (Hirao et al. 2020 ; Vaswani et al. 2017 ). In the context of AES, BERT follows specific procedures, as illustrated in Fig. 1 : (a) the tokenized prompts and essays are taken as input; (b) special tokens, such as [CLS] and [SEP], are added to mark the beginning and separation of prompts and essays; (c) the transformer encoder processes the prompt and essay sequences, resulting in hidden layer sequences; (d) the hidden layers corresponding to the [CLS] tokens (T[CLS]) represent distributed representations of the prompts and essays; and (e) a multilayer perceptron uses these distributed representations as input to obtain the final score (Hirao et al. 2020 ).

AES system with BERT (Hirao et al. 2020 ).

The training of BERT using a substantial amount of sentence data through the Masked Language Model (MLM) allows it to capture contextual information within the hidden layers. Consequently, BERT is expected to be capable of identifying artificial essays as invalid and assigning them lower scores (Mizumoto and Eguchi, 2023 ). In the context of AES for nonnative Japanese learners, Hirao et al. ( 2020 ) combined the long short-term memory (LSTM) model proposed by Hochreiter and Schmidhuber ( 1997 ) with BERT to develop a tailored automated Essay Scoring System. The findings of their study revealed that the BERT model outperformed both the conventional machine learning approach utilizing character-type features such as “kanji” and “hiragana”, as well as the standalone LSTM model. Takeuchi et al. ( 2021 ) presented an approach to Japanese AES that eliminates the requirement for pre-scored essays by relying solely on reference texts or a model answer for the essay task. They investigated multiple similarity evaluation methods, including frequency of morphemes, idf values calculated on Wikipedia, LSI, LDA, word-embedding vectors, and document vectors produced by BERT. The experimental findings revealed that the method utilizing the frequency of morphemes with idf values exhibited the strongest correlation with human-annotated scores across different essay tasks. The utilization of BERT in AES encounters several limitations. Firstly, essays often exceed the model’s maximum length limit. Second, only score labels are available for training, which restricts access to additional information.

Mizumoto and Eguchi ( 2023 ) were pioneers in employing the GPT model for AES in non-native English writing. Their study focused on evaluating the accuracy and reliability of AES using the GPT-3 text-davinci-003 model, analyzing a dataset of 12,100 essays from the corpus of nonnative written English (TOEFL11). The findings indicated that AES utilizing the GPT-3 model exhibited a certain degree of accuracy and reliability. They suggest that GPT-3-based AES systems hold the potential to provide support for human ratings. However, applying GPT model to AES presents a unique natural language processing (NLP) task that involves considerations such as nonnative language proficiency, the influence of the learner’s first language on the output in the target language, and identifying linguistic features that best indicate writing quality in a specific language. These linguistic features may differ morphologically or syntactically from those present in the learners’ first language, as observed in (1)–(3).

我-送了-他-一本-书

Wǒ-sòngle-tā-yī běn-shū

1 sg .-give. past- him-one .cl- book

“I gave him a book.”

Agglutinative

彼-に-本-を-あげ-まし-た

Kare-ni-hon-o-age-mashi-ta

3 sg .- dat -hon- acc- give.honorification. past

Inflectional

give, give-s, gave, given, giving

Additionally, the morphological agglutination and subject-object-verb (SOV) order in Japanese, along with its idiomatic expressions, pose additional challenges for applying language models in AES tasks (4).

足-が 棒-に なり-ました

Ashi-ga bo-ni nar-mashita

leg- nom stick- dat become- past

“My leg became like a stick (I am extremely tired).”

The example sentence provided demonstrates the morpho-syntactic structure of Japanese and the presence of an idiomatic expression. In this sentence, the verb “なる” (naru), meaning “to become”, appears at the end of the sentence. The verb stem “なり” (nari) is attached with morphemes indicating honorification (“ます” - mashu) and tense (“た” - ta), showcasing agglutination. While the sentence can be literally translated as “my leg became like a stick”, it carries an idiomatic interpretation that implies “I am extremely tired”.

To overcome this issue, CyberAgent Inc. ( 2023 ) has developed the Open-Calm series of language models specifically designed for Japanese. Open-Calm consists of pre-trained models available in various sizes, such as Small, Medium, Large, and 7b. Figure 2 depicts the fundamental structure of the Open-Calm model. A key feature of this architecture is the incorporation of the Lora Adapter and GPT-NeoX frameworks, which can enhance its language processing capabilities.

GPT-NeoX Model Architecture (Okgetheng and Takeuchi 2024 ).

In a recent study conducted by Okgetheng and Takeuchi ( 2024 ), they assessed the efficacy of Open-Calm language models in grading Japanese essays. The research utilized a dataset of approximately 300 essays, which were annotated by native Japanese educators. The findings of the study demonstrate the considerable potential of Open-Calm language models in automated Japanese essay scoring. Specifically, among the Open-Calm family, the Open-Calm Large model (referred to as OCLL) exhibited the highest performance. However, it is important to note that, as of the current date, the Open-Calm Large model does not offer public access to its server. Consequently, users are required to independently deploy and operate the environment for OCLL. In order to utilize OCLL, users must have a PC equipped with an NVIDIA GeForce RTX 3060 (8 or 12 GB VRAM).

In summary, while the potential of LLMs in automated scoring of nonnative Japanese essays has been demonstrated in two studies—BERT-driven AES (Hirao et al. 2020 ) and OCLL-based AES (Okgetheng and Takeuchi, 2024 )—the number of research efforts in this area remains limited.

Another significant challenge in applying LLMs to AES lies in prompt engineering and ensuring its reliability and effectiveness (Brown et al. 2020 ; Rae et al. 2021 ; Zhang et al. 2021 ). Various prompting strategies have been proposed, such as the zero-shot chain of thought (CoT) approach (Kojima et al. 2022 ), which involves manually crafting diverse and effective examples. However, manual efforts can lead to mistakes. To address this, Zhang et al. ( 2021 ) introduced an automatic CoT prompting method called Auto-CoT, which demonstrates matching or superior performance compared to the CoT paradigm. Another prompt framework is trees of thoughts, enabling a model to self-evaluate its progress at intermediate stages of problem-solving through deliberate reasoning (Yao et al. 2023 ).

Beyond linguistic studies, there has been a noticeable increase in the number of foreign workers in Japan and Japanese learners worldwide (Ministry of Health, Labor, and Welfare of Japan, 2022 ; Japan Foundation, 2021 ). However, existing assessment methods, such as the Japanese Language Proficiency Test (JLPT), J-CAT, and TTBJ Footnote 1 , primarily focus on reading, listening, vocabulary, and grammar skills, neglecting the evaluation of writing proficiency. As the number of workers and language learners continues to grow, there is a rising demand for an efficient AES system that can reduce costs and time for raters and be utilized for employment, examinations, and self-study purposes.

This study aims to explore the potential of LLM-based AES by comparing the effectiveness of five models: two LLMs (GPT Footnote 2 and BERT), one Japanese local LLM (OCLL), and two conventional machine learning-based methods (linguistic feature-based scoring tools - Jess and JWriter).

The research questions addressed in this study are as follows:

To what extent do the LLM-driven AES and linguistic feature-based AES, when used as automated tools to support human rating, accurately reflect test takers’ actual performance?

What influence does the prompt have on the accuracy and performance of LLM-based AES methods?

The subsequent sections of the manuscript cover the methodology, including the assessment measures for nonnative Japanese writing proficiency, criteria for prompts, and the dataset. The evaluation section focuses on the analysis of annotations and rating scores generated by LLM-driven and linguistic feature-based AES methods.

Methodology

The dataset utilized in this study was obtained from the International Corpus of Japanese as a Second Language (I-JAS) Footnote 3 . This corpus consisted of 1000 participants who represented 12 different first languages. For the study, the participants were given a story-writing task on a personal computer. They were required to write two stories based on the 4-panel illustrations titled “Picnic” and “The key” (see Appendix A). Background information for the participants was provided by the corpus, including their Japanese language proficiency levels assessed through two online tests: J-CAT and SPOT. These tests evaluated their reading, listening, vocabulary, and grammar abilities. The learners’ proficiency levels were categorized into six levels aligned with the Common European Framework of Reference for Languages (CEFR) and the Reference Framework for Japanese Language Education (RFJLE): A1, A2, B1, B2, C1, and C2. According to Lee et al. ( 2015 ), there is a high level of agreement (r = 0.86) between the J-CAT and SPOT assessments, indicating that the proficiency certifications provided by J-CAT are consistent with those of SPOT. However, it is important to note that the scores of J-CAT and SPOT do not have a one-to-one correspondence. In this study, the J-CAT scores were used as a benchmark to differentiate learners of different proficiency levels. A total of 1400 essays were utilized, representing the beginner (aligned with A1), A2, B1, B2, C1, and C2 levels based on the J-CAT scores. Table 1 provides information about the learners’ proficiency levels and their corresponding J-CAT and SPOT scores.

A dataset comprising a total of 1400 essays from the story writing tasks was collected. Among these, 714 essays were utilized to evaluate the reliability of the LLM-based AES method, while the remaining 686 essays were designated as development data to assess the LLM-based AES’s capability to distinguish participants with varying proficiency levels. The GPT 4 API was used in this study. A detailed explanation of the prompt-assessment criteria is provided in Section Prompt . All essays were sent to the model for measurement and scoring.

Measures of writing proficiency for nonnative Japanese

Japanese exhibits a morphologically agglutinative structure where morphemes are attached to the word stem to convey grammatical functions such as tense, aspect, voice, and honorifics, e.g. (5).

食べ-させ-られ-まし-た-か

tabe-sase-rare-mashi-ta-ka

[eat (stem)-causative-passive voice-honorification-tense. past-question marker]

Japanese employs nine case particles to indicate grammatical functions: the nominative case particle が (ga), the accusative case particle を (o), the genitive case particle の (no), the dative case particle に (ni), the locative/instrumental case particle で (de), the ablative case particle から (kara), the directional case particle へ (e), and the comitative case particle と (to). The agglutinative nature of the language, combined with the case particle system, provides an efficient means of distinguishing between active and passive voice, either through morphemes or case particles, e.g. 食べる taberu “eat concusive . ” (active voice); 食べられる taberareru “eat concusive . ” (passive voice). In the active voice, “パン を 食べる” (pan o taberu) translates to “to eat bread”. On the other hand, in the passive voice, it becomes “パン が 食べられた” (pan ga taberareta), which means “(the) bread was eaten”. Additionally, it is important to note that different conjugations of the same lemma are considered as one type in order to ensure a comprehensive assessment of the language features. For example, e.g., 食べる taberu “eat concusive . ”; 食べている tabeteiru “eat progress .”; 食べた tabeta “eat past . ” as one type.

To incorporate these features, previous research (Suzuki, 1999 ; Watanabe et al. 1988 ; Ishioka, 2001 ; Ishioka and Kameda, 2006 ; Hirao et al. 2020 ) has identified complexity, fluency, and accuracy as crucial factors for evaluating writing quality. These criteria are assessed through various aspects, including lexical richness (lexical density, diversity, and sophistication), syntactic complexity, and cohesion (Kyle et al. 2021 ; Mizumoto and Eguchi, 2023 ; Ure, 1971 ; Halliday, 1985 ; Barkaoui and Hadidi, 2020 ; Zenker and Kyle, 2021 ; Kim et al. 2018 ; Lu, 2017 ; Ortega, 2015 ). Therefore, this study proposes five scoring categories: lexical richness, syntactic complexity, cohesion, content elaboration, and grammatical accuracy. A total of 16 measures were employed to capture these categories. The calculation process and specific details of these measures can be found in Table 2 .

T-unit, first introduced by Hunt ( 1966 ), is a measure used for evaluating speech and composition. It serves as an indicator of syntactic development and represents the shortest units into which a piece of discourse can be divided without leaving any sentence fragments. In the context of Japanese language assessment, Sakoda and Hosoi ( 2020 ) utilized T-unit as the basic unit to assess the accuracy and complexity of Japanese learners’ speaking and storytelling. The calculation of T-units in Japanese follows the following principles:

A single main clause constitutes 1 T-unit, regardless of the presence or absence of dependent clauses, e.g. (6).

ケンとマリはピクニックに行きました (main clause): 1 T-unit.

If a sentence contains a main clause along with subclauses, each subclause is considered part of the same T-unit, e.g. (7).

天気が良かった の で (subclause)、ケンとマリはピクニックに行きました (main clause): 1 T-unit.

In the case of coordinate clauses, where multiple clauses are connected, each coordinated clause is counted separately. Thus, a sentence with coordinate clauses may have 2 T-units or more, e.g. (8).

ケンは地図で場所を探して (coordinate clause)、マリはサンドイッチを作りました (coordinate clause): 2 T-units.

Lexical diversity refers to the range of words used within a text (Engber, 1995 ; Kyle et al. 2021 ) and is considered a useful measure of the breadth of vocabulary in L n production (Jarvis, 2013a , 2013b ).

The type/token ratio (TTR) is widely recognized as a straightforward measure for calculating lexical diversity and has been employed in numerous studies. These studies have demonstrated a strong correlation between TTR and other methods of measuring lexical diversity (e.g., Bentz et al. 2016 ; Čech and Miroslav, 2018 ; Çöltekin and Taraka, 2018 ). TTR is computed by considering both the number of unique words (types) and the total number of words (tokens) in a given text. Given that the length of learners’ writing texts can vary, this study employs the moving average type-token ratio (MATTR) to mitigate the influence of text length. MATTR is calculated using a 50-word moving window. Initially, a TTR is determined for words 1–50 in an essay, followed by words 2–51, 3–52, and so on until the end of the essay is reached (Díez-Ortega and Kyle, 2023 ). The final MATTR scores were obtained by averaging the TTR scores for all 50-word windows. The following formula was employed to derive MATTR:

\({\rm{MATTR}}({\rm{W}})=\frac{{\sum }_{{\rm{i}}=1}^{{\rm{N}}-{\rm{W}}+1}{{\rm{F}}}_{{\rm{i}}}}{{\rm{W}}({\rm{N}}-{\rm{W}}+1)}\)

Here, N refers to the number of tokens in the corpus. W is the randomly selected token size (W < N). \({F}_{i}\) is the number of types in each window. The \({\rm{MATTR}}({\rm{W}})\) is the mean of a series of type-token ratios (TTRs) based on the word form for all windows. It is expected that individuals with higher language proficiency will produce texts with greater lexical diversity, as indicated by higher MATTR scores.

Lexical density was captured by the ratio of the number of lexical words to the total number of words (Lu, 2012 ). Lexical sophistication refers to the utilization of advanced vocabulary, often evaluated through word frequency indices (Crossley et al. 2013 ; Haberman, 2008 ; Kyle and Crossley, 2015 ; Laufer and Nation, 1995 ; Lu, 2012 ; Read, 2000 ). In line of writing, lexical sophistication can be interpreted as vocabulary breadth, which entails the appropriate usage of vocabulary items across various lexicon-grammatical contexts and registers (Garner et al. 2019 ; Kim et al. 2018 ; Kyle et al. 2018 ). In Japanese specifically, words are considered lexically sophisticated if they are not included in the “Japanese Education Vocabulary List Ver 1.0”. Footnote 4 Consequently, lexical sophistication was calculated by determining the number of sophisticated word types relative to the total number of words per essay. Furthermore, it has been suggested that, in Japanese writing, sentences should ideally have a length of no more than 40 to 50 characters, as this promotes readability. Therefore, the median and maximum sentence length can be considered as useful indices for assessment (Ishioka and Kameda, 2006 ).

Syntactic complexity was assessed based on several measures, including the mean length of clauses, verb phrases per T-unit, clauses per T-unit, dependent clauses per T-unit, complex nominals per clause, adverbial clauses per clause, coordinate phrases per clause, and mean dependency distance (MDD). The MDD reflects the distance between the governor and dependent positions in a sentence. A larger dependency distance indicates a higher cognitive load and greater complexity in syntactic processing (Liu, 2008 ; Liu et al. 2017 ). The MDD has been established as an efficient metric for measuring syntactic complexity (Jiang, Quyang, and Liu, 2019 ; Li and Yan, 2021 ). To calculate the MDD, the position numbers of the governor and dependent are subtracted, assuming that words in a sentence are assigned in a linear order, such as W1 … Wi … Wn. In any dependency relationship between words Wa and Wb, Wa is the governor and Wb is the dependent. The MDD of the entire sentence was obtained by taking the absolute value of governor – dependent:

MDD = \(\frac{1}{n}{\sum }_{i=1}^{n}|{\rm{D}}{{\rm{D}}}_{i}|\)

In this formula, \(n\) represents the number of words in the sentence, and \({DD}i\) is the dependency distance of the \({i}^{{th}}\) dependency relationship of a sentence. Building on this, the annotation of sentence ‘Mary-ga-John-ni-keshigomu-o-watashita was [Mary- top -John- dat -eraser- acc -give- past] ’. The sentence’s MDD would be 2. Table 3 provides the CSV file as a prompt for GPT 4.

Cohesion (semantic similarity) and content elaboration aim to capture the ideas presented in test taker’s essays. Cohesion was assessed using three measures: Synonym overlap/paragraph (topic), Synonym overlap/paragraph (keywords), and word2vec cosine similarity. Content elaboration and development were measured as the number of metadiscourse markers (type)/number of words. To capture content closely, this study proposed a novel-distance based representation, by encoding the cosine distance between the essay (by learner) and essay task’s (topic and keyword) i -vectors. The learner’s essay is decoded into a word sequence, and aligned to the essay task’ topic and keyword for log-likelihood measurement. The cosine distance reveals the content elaboration score in the leaners’ essay. The mathematical equation of cosine similarity between target-reference vectors is shown in (11), assuming there are i essays and ( L i , …. L n ) and ( N i , …. N n ) are the vectors representing the learner and task’s topic and keyword respectively. The content elaboration distance between L i and N i was calculated as follows:

\(\cos \left(\theta \right)=\frac{{\rm{L}}\,\cdot\, {\rm{N}}}{\left|{\rm{L}}\right|{\rm{|N|}}}=\frac{\mathop{\sum }\nolimits_{i=1}^{n}{L}_{i}{N}_{i}}{\sqrt{\mathop{\sum }\nolimits_{i=1}^{n}{L}_{i}^{2}}\sqrt{\mathop{\sum }\nolimits_{i=1}^{n}{N}_{i}^{2}}}\)

A high similarity value indicates a low difference between the two recognition outcomes, which in turn suggests a high level of proficiency in content elaboration.

To evaluate the effectiveness of the proposed measures in distinguishing different proficiency levels among nonnative Japanese speakers’ writing, we conducted a multi-faceted Rasch measurement analysis (Linacre, 1994 ). This approach applies measurement models to thoroughly analyze various factors that can influence test outcomes, including test takers’ proficiency, item difficulty, and rater severity, among others. The underlying principles and functionality of multi-faceted Rasch measurement are illustrated in (12).

\(\log \left(\frac{{P}_{{nijk}}}{{P}_{{nij}(k-1)}}\right)={B}_{n}-{D}_{i}-{C}_{j}-{F}_{k}\)

(12) defines the logarithmic transformation of the probability ratio ( P nijk /P nij(k-1) )) as a function of multiple parameters. Here, n represents the test taker, i denotes a writing proficiency measure, j corresponds to the human rater, and k represents the proficiency score. The parameter B n signifies the proficiency level of test taker n (where n ranges from 1 to N). D j represents the difficulty parameter of test item i (where i ranges from 1 to L), while C j represents the severity of rater j (where j ranges from 1 to J). Additionally, F k represents the step difficulty for a test taker to move from score ‘k-1’ to k . P nijk refers to the probability of rater j assigning score k to test taker n for test item i . P nij(k-1) represents the likelihood of test taker n being assigned score ‘k-1’ by rater j for test item i . Each facet within the test is treated as an independent parameter and estimated within the same reference framework. To evaluate the consistency of scores obtained through both human and computer analysis, we utilized the Infit mean-square statistic. This statistic is a chi-square measure divided by the degrees of freedom and is weighted with information. It demonstrates higher sensitivity to unexpected patterns in responses to items near a person’s proficiency level (Linacre, 2002 ). Fit statistics are assessed based on predefined thresholds for acceptable fit. For the Infit MNSQ, which has a mean of 1.00, different thresholds have been suggested. Some propose stricter thresholds ranging from 0.7 to 1.3 (Bond et al. 2021 ), while others suggest more lenient thresholds ranging from 0.5 to 1.5 (Eckes, 2009 ). In this study, we adopted the criterion of 0.70–1.30 for the Infit MNSQ.

Moving forward, we can now proceed to assess the effectiveness of the 16 proposed measures based on five criteria for accurately distinguishing various levels of writing proficiency among non-native Japanese speakers. To conduct this evaluation, we utilized the development dataset from the I-JAS corpus, as described in Section Dataset . Table 4 provides a measurement report that presents the performance details of the 14 metrics under consideration. The measure separation was found to be 4.02, indicating a clear differentiation among the measures. The reliability index for the measure separation was 0.891, suggesting consistency in the measurement. Similarly, the person separation reliability index was 0.802, indicating the accuracy of the assessment in distinguishing between individuals. All 16 measures demonstrated Infit mean squares within a reasonable range, ranging from 0.76 to 1.28. The Synonym overlap/paragraph (topic) measure exhibited a relatively high outfit mean square of 1.46, although the Infit mean square falls within an acceptable range. The standard error for the measures ranged from 0.13 to 0.28, indicating the precision of the estimates.

Table 5 further illustrated the weights assigned to different linguistic measures for score prediction, with higher weights indicating stronger correlations between those measures and higher scores. Specifically, the following measures exhibited higher weights compared to others: moving average type token ratio per essay has a weight of 0.0391. Mean dependency distance had a weight of 0.0388. Mean length of clause, calculated by dividing the number of words by the number of clauses, had a weight of 0.0374. Complex nominals per T-unit, calculated by dividing the number of complex nominals by the number of T-units, had a weight of 0.0379. Coordinate phrases rate, calculated by dividing the number of coordinate phrases by the number of clauses, had a weight of 0.0325. Grammatical error rate, representing the number of errors per essay, had a weight of 0.0322.

Criteria (output indicator)

The criteria used to evaluate the writing ability in this study were based on CEFR, which follows a six-point scale ranging from A1 to C2. To assess the quality of Japanese writing, the scoring criteria from Table 6 were utilized. These criteria were derived from the IELTS writing standards and served as assessment guidelines and prompts for the written output.

A prompt is a question or detailed instruction that is provided to the model to obtain a proper response. After several pilot experiments, we decided to provide the measures (Section Measures of writing proficiency for nonnative Japanese ) as the input prompt and use the criteria (Section Criteria (output indicator) ) as the output indicator. Regarding the prompt language, considering that the LLM was tasked with rating Japanese essays, would prompt in Japanese works better Footnote 5 ? We conducted experiments comparing the performance of GPT-4 using both English and Japanese prompts. Additionally, we utilized the Japanese local model OCLL with Japanese prompts. Multiple trials were conducted using the same sample. Regardless of the prompt language used, we consistently obtained the same grading results with GPT-4, which assigned a grade of B1 to the writing sample. This suggested that GPT-4 is reliable and capable of producing consistent ratings regardless of the prompt language. On the other hand, when we used Japanese prompts with the Japanese local model “OCLL”, we encountered inconsistent grading results. Out of 10 attempts with OCLL, only 6 yielded consistent grading results (B1), while the remaining 4 showed different outcomes, including A1 and B2 grades. These findings indicated that the language of the prompt was not the determining factor for reliable AES. Instead, the size of the training data and the model parameters played crucial roles in achieving consistent and reliable AES results for the language model.

The following is the utilized prompt, which details all measures and requires the LLM to score the essays using holistic and trait scores.

Please evaluate Japanese essays written by Japanese learners and assign a score to each essay on a six-point scale, ranging from A1, A2, B1, B2, C1 to C2. Additionally, please provide trait scores and display the calculation process for each trait score. The scoring should be based on the following criteria:

Moving average type-token ratio.

Number of lexical words (token) divided by the total number of words per essay.

Number of sophisticated word types divided by the total number of words per essay.

Mean length of clause.

Verb phrases per T-unit.

Clauses per T-unit.

Dependent clauses per T-unit.

Complex nominals per clause.

Adverbial clauses per clause.

Coordinate phrases per clause.

Mean dependency distance.

Synonym overlap paragraph (topic and keywords).

Word2vec cosine similarity.

Connectives per essay.

Conjunctions per essay.

Number of metadiscourse markers (types) divided by the total number of words.

Number of errors per essay.

Japanese essay text

出かける前に二人が地図を見ている間に、サンドイッチを入れたバスケットに犬が入ってしまいました。それに気づかずに二人は楽しそうに出かけて行きました。やがて突然犬がバスケットから飛び出し、二人は驚きました。バスケット の 中を見ると、食べ物はすべて犬に食べられていて、二人は困ってしまいました。(ID_JJJ01_SW1)

The score of the example above was B1. Figure 3 provides an example of holistic and trait scores provided by GPT-4 (with a prompt indicating all measures) via Bing Footnote 6 .

Example of GPT-4 AES and feedback (with a prompt indicating all measures).

Statistical analysis

The aim of this study is to investigate the potential use of LLM for nonnative Japanese AES. It seeks to compare the scoring outcomes obtained from feature-based AES tools, which rely on conventional machine learning technology (i.e. Jess, JWriter), with those generated by AI-driven AES tools utilizing deep learning technology (BERT, GPT, OCLL). To assess the reliability of a computer-assisted annotation tool, the study initially established human-human agreement as the benchmark measure. Subsequently, the performance of the LLM-based method was evaluated by comparing it to human-human agreement.

To assess annotation agreement, the study employed standard measures such as precision, recall, and F-score (Brants 2000 ; Lu 2010 ), along with the quadratically weighted kappa (QWK) to evaluate the consistency and agreement in the annotation process. Assume A and B represent human annotators. When comparing the annotations of the two annotators, the following results are obtained. The evaluation of precision, recall, and F-score metrics was illustrated in equations (13) to (15).

\({\rm{Recall}}(A,B)=\frac{{\rm{Number}}\,{\rm{of}}\,{\rm{identical}}\,{\rm{nodes}}\,{\rm{in}}\,A\,{\rm{and}}\,B}{{\rm{Number}}\,{\rm{of}}\,{\rm{nodes}}\,{\rm{in}}\,A}\)

\({\rm{Precision}}(A,\,B)=\frac{{\rm{Number}}\,{\rm{of}}\,{\rm{identical}}\,{\rm{nodes}}\,{\rm{in}}\,A\,{\rm{and}}\,B}{{\rm{Number}}\,{\rm{of}}\,{\rm{nodes}}\,{\rm{in}}\,B}\)

The F-score is the harmonic mean of recall and precision:

\({\rm{F}}-{\rm{score}}=\frac{2* ({\rm{Precision}}* {\rm{Recall}})}{{\rm{Precision}}+{\rm{Recall}}}\)

The highest possible value of an F-score is 1.0, indicating perfect precision and recall, and the lowest possible value is 0, if either precision or recall are zero.

In accordance with Taghipour and Ng ( 2016 ), the calculation of QWK involves two steps:

Step 1: Construct a weight matrix W as follows:

\({W}_{{ij}}=\frac{{(i-j)}^{2}}{{(N-1)}^{2}}\)

i represents the annotation made by the tool, while j represents the annotation made by a human rater. N denotes the total number of possible annotations. Matrix O is subsequently computed, where O_( i, j ) represents the count of data annotated by the tool ( i ) and the human annotator ( j ). On the other hand, E refers to the expected count matrix, which undergoes normalization to ensure that the sum of elements in E matches the sum of elements in O.

Step 2: With matrices O and E, the QWK is obtained as follows:

K = 1- \(\frac{\sum i,j{W}_{i,j}\,{O}_{i,j}}{\sum i,j{W}_{i,j}\,{E}_{i,j}}\)

The value of the quadratic weighted kappa increases as the level of agreement improves. Further, to assess the accuracy of LLM scoring, the proportional reductive mean square error (PRMSE) was employed. The PRMSE approach takes into account the variability observed in human ratings to estimate the rater error, which is then subtracted from the variance of the human labels. This calculation provides an overall measure of agreement between the automated scores and true scores (Haberman et al. 2015 ; Loukina et al. 2020 ; Taghipour and Ng, 2016 ). The computation of PRMSE involves the following steps:

Step 1: Calculate the mean squared errors (MSEs) for the scoring outcomes of the computer-assisted tool (MSE tool) and the human scoring outcomes (MSE human).

Step 2: Determine the PRMSE by comparing the MSE of the computer-assisted tool (MSE tool) with the MSE from human raters (MSE human), using the following formula:

\({\rm{PRMSE}}=1-\frac{({\rm{MSE}}\,{\rm{tool}})\,}{({\rm{MSE}}\,{\rm{human}})\,}=1-\,\frac{{\sum }_{i}^{n}=1{({{\rm{y}}}_{i}-{\hat{{\rm{y}}}}_{{\rm{i}}})}^{2}}{{\sum }_{i}^{n}=1{({{\rm{y}}}_{i}-\hat{{\rm{y}}})}^{2}}\)

In the numerator, ŷi represents the scoring outcome predicted by a specific LLM-driven AES system for a given sample. The term y i − ŷ i represents the difference between this predicted outcome and the mean value of all LLM-driven AES systems’ scoring outcomes. It quantifies the deviation of the specific LLM-driven AES system’s prediction from the average prediction of all LLM-driven AES systems. In the denominator, y i − ŷ represents the difference between the scoring outcome provided by a specific human rater for a given sample and the mean value of all human raters’ scoring outcomes. It measures the discrepancy between the specific human rater’s score and the average score given by all human raters. The PRMSE is then calculated by subtracting the ratio of the MSE tool to the MSE human from 1. PRMSE falls within the range of 0 to 1, with larger values indicating reduced errors in LLM’s scoring compared to those of human raters. In other words, a higher PRMSE implies that LLM’s scoring demonstrates greater accuracy in predicting the true scores (Loukina et al. 2020 ). The interpretation of kappa values, ranging from 0 to 1, is based on the work of Landis and Koch ( 1977 ). Specifically, the following categories are assigned to different ranges of kappa values: −1 indicates complete inconsistency, 0 indicates random agreement, 0.0 ~ 0.20 indicates extremely low level of agreement (slight), 0.21 ~ 0.40 indicates moderate level of agreement (fair), 0.41 ~ 0.60 indicates medium level of agreement (moderate), 0.61 ~ 0.80 indicates high level of agreement (substantial), 0.81 ~ 1 indicates almost perfect level of agreement. All statistical analyses were executed using Python script.

Results and discussion

Annotation reliability of the llm.

This section focuses on assessing the reliability of the LLM’s annotation and scoring capabilities. To evaluate the reliability, several tests were conducted simultaneously, aiming to achieve the following objectives:

Assess the LLM’s ability to differentiate between test takers with varying levels of oral proficiency.

Determine the level of agreement between the annotations and scoring performed by the LLM and those done by human raters.

The evaluation of the results encompassed several metrics, including: precision, recall, F-Score, quadratically-weighted kappa, proportional reduction of mean squared error, Pearson correlation, and multi-faceted Rasch measurement.

Inter-annotator agreement (human–human annotator agreement)

We started with an agreement test of the two human annotators. Two trained annotators were recruited to determine the writing task data measures. A total of 714 scripts, as the test data, was utilized. Each analysis lasted 300–360 min. Inter-annotator agreement was evaluated using the standard measures of precision, recall, and F-score and QWK. Table 7 presents the inter-annotator agreement for the various indicators. As shown, the inter-annotator agreement was fairly high, with F-scores ranging from 1.0 for sentence and word number to 0.666 for grammatical errors.

The findings from the QWK analysis provided further confirmation of the inter-annotator agreement. The QWK values covered a range from 0.950 ( p  = 0.000) for sentence and word number to 0.695 for synonym overlap number (keyword) and grammatical errors ( p  = 0.001).

Agreement of annotation outcomes between human and LLM

To evaluate the consistency between human annotators and LLM annotators (BERT, GPT, OCLL) across the indices, the same test was conducted. The results of the inter-annotator agreement (F-score) between LLM and human annotation are provided in Appendix B-D. The F-scores ranged from 0.706 for Grammatical error # for OCLL-human to a perfect 1.000 for GPT-human, for sentences, clauses, T-units, and words. These findings were further supported by the QWK analysis, which showed agreement levels ranging from 0.807 ( p  = 0.001) for metadiscourse markers for OCLL-human to 0.962 for words ( p  = 0.000) for GPT-human. The findings demonstrated that the LLM annotation achieved a significant level of accuracy in identifying measurement units and counts.

Reliability of LLM-driven AES’s scoring and discriminating proficiency levels

This section examines the reliability of the LLM-driven AES scoring through a comparison of the scoring outcomes produced by human raters and the LLM ( Reliability of LLM-driven AES scoring ). It also assesses the effectiveness of the LLM-based AES system in differentiating participants with varying proficiency levels ( Reliability of LLM-driven AES discriminating proficiency levels ).

Reliability of LLM-driven AES scoring

Table 8 summarizes the QWK coefficient analysis between the scores computed by the human raters and the GPT-4 for the individual essays from I-JAS Footnote 7 . As shown, the QWK of all measures ranged from k  = 0.819 for lexical density (number of lexical words (tokens)/number of words per essay) to k  = 0.644 for word2vec cosine similarity. Table 9 further presents the Pearson correlations between the 16 writing proficiency measures scored by human raters and GPT 4 for the individual essays. The correlations ranged from 0.672 for syntactic complexity to 0.734 for grammatical accuracy. The correlations between the writing proficiency scores assigned by human raters and the BERT-based AES system were found to range from 0.661 for syntactic complexity to 0.713 for grammatical accuracy. The correlations between the writing proficiency scores given by human raters and the OCLL-based AES system ranged from 0.654 for cohesion to 0.721 for grammatical accuracy. These findings indicated an alignment between the assessments made by human raters and both the BERT-based and OCLL-based AES systems in terms of various aspects of writing proficiency.

Reliability of LLM-driven AES discriminating proficiency levels

After validating the reliability of the LLM’s annotation and scoring, the subsequent objective was to evaluate its ability to distinguish between various proficiency levels. For this analysis, a dataset of 686 individual essays was utilized. Table 10 presents a sample of the results, summarizing the means, standard deviations, and the outcomes of the one-way ANOVAs based on the measures assessed by the GPT-4 model. A post hoc multiple comparison test, specifically the Bonferroni test, was conducted to identify any potential differences between pairs of levels.

As the results reveal, seven measures presented linear upward or downward progress across the three proficiency levels. These were marked in bold in Table 10 and comprise one measure of lexical richness, i.e. MATTR (lexical diversity); four measures of syntactic complexity, i.e. MDD (mean dependency distance), MLC (mean length of clause), CNT (complex nominals per T-unit), CPC (coordinate phrases rate); one cohesion measure, i.e. word2vec cosine similarity and GER (grammatical error rate). Regarding the ability of the sixteen measures to distinguish adjacent proficiency levels, the Bonferroni tests indicated that statistically significant differences exist between the primary level and the intermediate level for MLC and GER. One measure of lexical richness, namely LD, along with three measures of syntactic complexity (VPT, CT, DCT, ACC), two measures of cohesion (SOPT, SOPK), and one measure of content elaboration (IMM), exhibited statistically significant differences between proficiency levels. However, these differences did not demonstrate a linear progression between adjacent proficiency levels. No significant difference was observed in lexical sophistication between proficiency levels.

To summarize, our study aimed to evaluate the reliability and differentiation capabilities of the LLM-driven AES method. For the first objective, we assessed the LLM’s ability to differentiate between test takers with varying levels of oral proficiency using precision, recall, F-Score, and quadratically-weighted kappa. Regarding the second objective, we compared the scoring outcomes generated by human raters and the LLM to determine the level of agreement. We employed quadratically-weighted kappa and Pearson correlations to compare the 16 writing proficiency measures for the individual essays. The results confirmed the feasibility of using the LLM for annotation and scoring in AES for nonnative Japanese. As a result, Research Question 1 has been addressed.

Comparison of BERT-, GPT-, OCLL-based AES, and linguistic-feature-based computation methods

This section aims to compare the effectiveness of five AES methods for nonnative Japanese writing, i.e. LLM-driven approaches utilizing BERT, GPT, and OCLL, linguistic feature-based approaches using Jess and JWriter. The comparison was conducted by comparing the ratings obtained from each approach with human ratings. All ratings were derived from the dataset introduced in Dataset . To facilitate the comparison, the agreement between the automated methods and human ratings was assessed using QWK and PRMSE. The performance of each approach was summarized in Table 11 .

The QWK coefficient values indicate that LLMs (GPT, BERT, OCLL) and human rating outcomes demonstrated higher agreement compared to feature-based AES methods (Jess and JWriter) in assessing writing proficiency criteria, including lexical richness, syntactic complexity, content, and grammatical accuracy. Among the LLMs, the GPT-4 driven AES and human rating outcomes showed the highest agreement in all criteria, except for syntactic complexity. The PRMSE values suggest that the GPT-based method outperformed linguistic feature-based methods and other LLM-based approaches. Moreover, an interesting finding emerged during the study: the agreement coefficient between GPT-4 and human scoring was even higher than the agreement between different human raters themselves. This discovery highlights the advantage of GPT-based AES over human rating. Ratings involve a series of processes, including reading the learners’ writing, evaluating the content and language, and assigning scores. Within this chain of processes, various biases can be introduced, stemming from factors such as rater biases, test design, and rating scales. These biases can impact the consistency and objectivity of human ratings. GPT-based AES may benefit from its ability to apply consistent and objective evaluation criteria. By prompting the GPT model with detailed writing scoring rubrics and linguistic features, potential biases in human ratings can be mitigated. The model follows a predefined set of guidelines and does not possess the same subjective biases that human raters may exhibit. This standardization in the evaluation process contributes to the higher agreement observed between GPT-4 and human scoring. Section Prompt strategy of the study delves further into the role of prompts in the application of LLMs to AES. It explores how the choice and implementation of prompts can impact the performance and reliability of LLM-based AES methods. Furthermore, it is important to acknowledge the strengths of the local model, i.e. the Japanese local model OCLL, which excels in processing certain idiomatic expressions. Nevertheless, our analysis indicated that GPT-4 surpasses local models in AES. This superior performance can be attributed to the larger parameter size of GPT-4, estimated to be between 500 billion and 1 trillion, which exceeds the sizes of both BERT and the local model OCLL.

Prompt strategy

In the context of prompt strategy, Mizumoto and Eguchi ( 2023 ) conducted a study where they applied the GPT-3 model to automatically score English essays in the TOEFL test. They found that the accuracy of the GPT model alone was moderate to fair. However, when they incorporated linguistic measures such as cohesion, syntactic complexity, and lexical features alongside the GPT model, the accuracy significantly improved. This highlights the importance of prompt engineering and providing the model with specific instructions to enhance its performance. In this study, a similar approach was taken to optimize the performance of LLMs. GPT-4, which outperformed BERT and OCLL, was selected as the candidate model. Model 1 was used as the baseline, representing GPT-4 without any additional prompting. Model 2, on the other hand, involved GPT-4 prompted with 16 measures that included scoring criteria, efficient linguistic features for writing assessment, and detailed measurement units and calculation formulas. The remaining models (Models 3 to 18) utilized GPT-4 prompted with individual measures. The performance of these 18 different models was assessed using the output indicators described in Section Criteria (output indicator) . By comparing the performances of these models, the study aimed to understand the impact of prompt engineering on the accuracy and effectiveness of GPT-4 in AES tasks.

Based on the PRMSE scores presented in Fig. 4 , it was observed that Model 1, representing GPT-4 without any additional prompting, achieved a fair level of performance. However, Model 2, which utilized GPT-4 prompted with all measures, outperformed all other models in terms of PRMSE score, achieving a score of 0.681. These results indicate that the inclusion of specific measures and prompts significantly enhanced the performance of GPT-4 in AES. Among the measures, syntactic complexity was found to play a particularly significant role in improving the accuracy of GPT-4 in assessing writing quality. Following that, lexical diversity emerged as another important factor contributing to the model’s effectiveness. The study suggests that a well-prompted GPT-4 can serve as a valuable tool to support human assessors in evaluating writing quality. By utilizing GPT-4 as an automated scoring tool, the evaluation biases associated with human raters can be minimized. This has the potential to empower teachers by allowing them to focus on designing writing tasks and guiding writing strategies, while leveraging the capabilities of GPT-4 for efficient and reliable scoring.

PRMSE scores of the 18 AES models.

This study aimed to investigate two main research questions: the feasibility of utilizing LLMs for AES and the impact of prompt engineering on the application of LLMs in AES.

To address the first objective, the study compared the effectiveness of five different models: GPT, BERT, the Japanese local LLM (OCLL), and two conventional machine learning-based AES tools (Jess and JWriter). The PRMSE values indicated that the GPT-4-based method outperformed other LLMs (BERT, OCLL) and linguistic feature-based computational methods (Jess and JWriter) across various writing proficiency criteria. Furthermore, the agreement coefficient between GPT-4 and human scoring surpassed the agreement among human raters themselves, highlighting the potential of using the GPT-4 tool to enhance AES by reducing biases and subjectivity, saving time, labor, and cost, and providing valuable feedback for self-study. Regarding the second goal, the role of prompt design was investigated by comparing 18 models, including a baseline model, a model prompted with all measures, and 16 models prompted with one measure at a time. GPT-4, which outperformed BERT and OCLL, was selected as the candidate model. The PRMSE scores of the models showed that GPT-4 prompted with all measures achieved the best performance, surpassing the baseline and other models.

In conclusion, this study has demonstrated the potential of LLMs in supporting human rating in assessments. By incorporating automation, we can save time and resources while reducing biases and subjectivity inherent in human rating processes. Automated language assessments offer the advantage of accessibility, providing equal opportunities and economic feasibility for individuals who lack access to traditional assessment centers or necessary resources. LLM-based language assessments provide valuable feedback and support to learners, aiding in the enhancement of their language proficiency and the achievement of their goals. This personalized feedback can cater to individual learner needs, facilitating a more tailored and effective language-learning experience.

There are three important areas that merit further exploration. First, prompt engineering requires attention to ensure optimal performance of LLM-based AES across different language types. This study revealed that GPT-4, when prompted with all measures, outperformed models prompted with fewer measures. Therefore, investigating and refining prompt strategies can enhance the effectiveness of LLMs in automated language assessments. Second, it is crucial to explore the application of LLMs in second-language assessment and learning for oral proficiency, as well as their potential in under-resourced languages. Recent advancements in self-supervised machine learning techniques have significantly improved automatic speech recognition (ASR) systems, opening up new possibilities for creating reliable ASR systems, particularly for under-resourced languages with limited data. However, challenges persist in the field of ASR. First, ASR assumes correct word pronunciation for automatic pronunciation evaluation, which proves challenging for learners in the early stages of language acquisition due to diverse accents influenced by their native languages. Accurately segmenting short words becomes problematic in such cases. Second, developing precise audio-text transcriptions for languages with non-native accented speech poses a formidable task. Last, assessing oral proficiency levels involves capturing various linguistic features, including fluency, pronunciation, accuracy, and complexity, which are not easily captured by current NLP technology.

Data availability

The dataset utilized was obtained from the International Corpus of Japanese as a Second Language (I-JAS). The data URLs: [ https://www2.ninjal.ac.jp/jll/lsaj/ihome2.html ].

J-CAT and TTBJ are two computerized adaptive tests used to assess Japanese language proficiency.

SPOT is a specific component of the TTBJ test.

J-CAT: https://www.j-cat2.org/html/ja/pages/interpret.html

SPOT: https://ttbj.cegloc.tsukuba.ac.jp/p1.html#SPOT .

The study utilized a prompt-based GPT-4 model, developed by OpenAI, which has an impressive architecture with 1.8 trillion parameters across 120 layers. GPT-4 was trained on a vast dataset of 13 trillion tokens, using two stages: initial training on internet text datasets to predict the next token, and subsequent fine-tuning through reinforcement learning from human feedback.

https://www2.ninjal.ac.jp/jll/lsaj/ihome2-en.html .

http://jhlee.sakura.ne.jp/JEV/ by Japanese Learning Dictionary Support Group 2015.

We express our sincere gratitude to the reviewer for bringing this matter to our attention.

On February 7, 2023, Microsoft began rolling out a major overhaul to Bing that included a new chatbot feature based on OpenAI’s GPT-4 (Bing.com).

Appendix E-F present the analysis results of the QWK coefficient between the scores computed by the human raters and the BERT, OCLL models.

Attali Y, Burstein J (2006) Automated essay scoring with e-rater® V.2. J. Technol., Learn. Assess., 4

Barkaoui K, Hadidi A (2020) Assessing Change in English Second Language Writing Performance (1st ed.). Routledge, New York. https://doi.org/10.4324/9781003092346

Bentz C, Tatyana R, Koplenig A, Tanja S (2016) A comparison between morphological complexity. measures: Typological data vs. language corpora. In Proceedings of the workshop on computational linguistics for linguistic complexity (CL4LC), 142–153. Osaka, Japan: The COLING 2016 Organizing Committee

Bond TG, Yan Z, Heene M (2021) Applying the Rasch model: Fundamental measurement in the human sciences (4th ed). Routledge

Brants T (2000) Inter-annotator agreement for a German newspaper corpus. Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00), Athens, Greece, 31 May-2 June, European Language Resources Association

Brown TB, Mann B, Ryder N, et al. (2020) Language models are few-shot learners. Advances in Neural Information Processing Systems, Online, 6–12 December, Curran Associates, Inc., Red Hook, NY

Burstein J (2003) The E-rater scoring engine: Automated essay scoring with natural language processing. In Shermis MD and Burstein JC (ed) Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Čech R, Miroslav K (2018) Morphological richness of text. In Masako F, Václav C (ed) Taming the corpus: From inflection and lexis to interpretation, 63–77. Cham, Switzerland: Springer Nature

Çöltekin Ç, Taraka, R (2018) Exploiting Universal Dependencies treebanks for measuring morphosyntactic complexity. In Aleksandrs B, Christian B (ed), Proceedings of first workshop on measuring language complexity, 1–7. Torun, Poland

Crossley SA, Cobb T, McNamara DS (2013) Comparing count-based and band-based indices of word frequency: Implications for active vocabulary research and pedagogical applications. System 41:965–981. https://doi.org/10.1016/j.system.2013.08.002

Article   Google Scholar  

Crossley SA, McNamara DS (2016) Say more and be more coherent: How text elaboration and cohesion can increase writing quality. J. Writ. Res. 7:351–370

CyberAgent Inc (2023) Open-Calm series of Japanese language models. Retrieved from: https://www.cyberagent.co.jp/news/detail/id=28817

Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota, 2–7 June, pp. 4171–4186. Association for Computational Linguistics

Diez-Ortega M, Kyle K (2023) Measuring the development of lexical richness of L2 Spanish: a longitudinal learner corpus study. Studies in Second Language Acquisition 1-31

Eckes T (2009) On common ground? How raters perceive scoring criteria in oral proficiency testing. In Brown A, Hill K (ed) Language testing and evaluation 13: Tasks and criteria in performance assessment (pp. 43–73). Peter Lang Publishing

Elliot S (2003) IntelliMetric: from here to validity. In: Shermis MD, Burstein JC (ed) Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Google Scholar  

Engber CA (1995) The relationship of lexical proficiency to the quality of ESL compositions. J. Second Lang. Writ. 4:139–155

Garner J, Crossley SA, Kyle K (2019) N-gram measures and L2 writing proficiency. System 80:176–187. https://doi.org/10.1016/j.system.2018.12.001

Haberman SJ (2008) When can subscores have value? J. Educat. Behav. Stat., 33:204–229

Haberman SJ, Yao L, Sinharay S (2015) Prediction of true test scores from observed item scores and ancillary data. Brit. J. Math. Stat. Psychol. 68:363–385

Halliday MAK (1985) Spoken and Written Language. Deakin University Press, Melbourne, Australia

Hirao R, Arai M, Shimanaka H et al. (2020) Automated essay scoring system for nonnative Japanese learners. Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pp. 1250–1257. European Language Resources Association

Hunt KW (1966) Recent Measures in Syntactic Development. Elementary English, 43(7), 732–739. http://www.jstor.org/stable/41386067

Ishioka T (2001) About e-rater, a computer-based automatic scoring system for essays [Konpyūta ni yoru essei no jidō saiten shisutemu e − rater ni tsuite]. University Entrance Examination. Forum [Daigaku nyūshi fōramu] 24:71–76

Hochreiter S, Schmidhuber J (1997) Long short- term memory. Neural Comput. 9(8):1735–1780

Article   CAS   PubMed   Google Scholar  

Ishioka T, Kameda M (2006) Automated Japanese essay scoring system based on articles written by experts. Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, 17–18 July 2006, pp. 233-240. Association for Computational Linguistics, USA

Japan Foundation (2021) Retrieved from: https://www.jpf.gp.jp/j/project/japanese/survey/result/dl/survey2021/all.pdf

Jarvis S (2013a) Defining and measuring lexical diversity. In Jarvis S, Daller M (ed) Vocabulary knowledge: Human ratings and automated measures (Vol. 47, pp. 13–44). John Benjamins. https://doi.org/10.1075/sibil.47.03ch1

Jarvis S (2013b) Capturing the diversity in lexical diversity. Lang. Learn. 63:87–106. https://doi.org/10.1111/j.1467-9922.2012.00739.x

Jiang J, Quyang J, Liu H (2019) Interlanguage: A perspective of quantitative linguistic typology. Lang. Sci. 74:85–97

Kim M, Crossley SA, Kyle K (2018) Lexical sophistication as a multidimensional phenomenon: Relations to second language lexical proficiency, development, and writing quality. Mod. Lang. J. 102(1):120–141. https://doi.org/10.1111/modl.12447

Kojima T, Gu S, Reid M et al. (2022) Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, New Orleans, LA, 29 November-1 December, Curran Associates, Inc., Red Hook, NY

Kyle K, Crossley SA (2015) Automatically assessing lexical sophistication: Indices, tools, findings, and application. TESOL Q 49:757–786

Kyle K, Crossley SA, Berger CM (2018) The tool for the automatic analysis of lexical sophistication (TAALES): Version 2.0. Behav. Res. Methods 50:1030–1046. https://doi.org/10.3758/s13428-017-0924-4

Article   PubMed   Google Scholar  

Kyle K, Crossley SA, Jarvis S (2021) Assessing the validity of lexical diversity using direct judgements. Lang. Assess. Q. 18:154–170. https://doi.org/10.1080/15434303.2020.1844205

Landauer TK, Laham D, Foltz PW (2003) Automated essay scoring and annotation of essays with the Intelligent Essay Assessor. In Shermis MD, Burstein JC (ed), Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 159–174

Laufer B, Nation P (1995) Vocabulary size and use: Lexical richness in L2 written production. Appl. Linguist. 16:307–322. https://doi.org/10.1093/applin/16.3.307

Lee J, Hasebe Y (2017) jWriter Learner Text Evaluator, URL: https://jreadability.net/jwriter/

Lee J, Kobayashi N, Sakai T, Sakota K (2015) A Comparison of SPOT and J-CAT Based on Test Analysis [Tesuto bunseki ni motozuku ‘SPOT’ to ‘J-CAT’ no hikaku]. Research on the Acquisition of Second Language Japanese [Dainigengo to shite no nihongo no shūtoku kenkyū] (18) 53–69

Li W, Yan J (2021) Probability distribution of dependency distance based on a Treebank of. Japanese EFL Learners’ Interlanguage. J. Quant. Linguist. 28(2):172–186. https://doi.org/10.1080/09296174.2020.1754611

Article   MathSciNet   Google Scholar  

Linacre JM (2002) Optimizing rating scale category effectiveness. J. Appl. Meas. 3(1):85–106

PubMed   Google Scholar  

Linacre JM (1994) Constructing measurement with a Many-Facet Rasch Model. In Wilson M (ed) Objective measurement: Theory into practice, Volume 2 (pp. 129–144). Norwood, NJ: Ablex

Liu H (2008) Dependency distance as a metric of language comprehension difficulty. J. Cognitive Sci. 9:159–191

Liu H, Xu C, Liang J (2017) Dependency distance: A new perspective on syntactic patterns in natural languages. Phys. Life Rev. 21. https://doi.org/10.1016/j.plrev.2017.03.002

Loukina A, Madnani N, Cahill A, et al. (2020) Using PRMSE to evaluate automated scoring systems in the presence of label noise. Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, Seattle, WA, USA → Online, 10 July, pp. 18–29. Association for Computational Linguistics

Lu X (2010) Automatic analysis of syntactic complexity in second language writing. Int. J. Corpus Linguist. 15:474–496

Lu X (2012) The relationship of lexical richness to the quality of ESL learners’ oral narratives. Mod. Lang. J. 96:190–208

Lu X (2017) Automated measurement of syntactic complexity in corpus-based L2 writing research and implications for writing assessment. Lang. Test. 34:493–511

Lu X, Hu R (2022) Sense-aware lexical sophistication indices and their relationship to second language writing quality. Behav. Res. Method. 54:1444–1460. https://doi.org/10.3758/s13428-021-01675-6

Ministry of Health, Labor, and Welfare of Japan (2022) Retrieved from: https://www.mhlw.go.jp/stf/newpage_30367.html

Mizumoto A, Eguchi M (2023) Exploring the potential of using an AI language model for automated essay scoring. Res. Methods Appl. Linguist. 3:100050

Okgetheng B, Takeuchi K (2024) Estimating Japanese Essay Grading Scores with Large Language Models. Proceedings of 30th Annual Conference of the Language Processing Society in Japan, March 2024

Ortega L (2015) Second language learning explained? SLA across 10 contemporary theories. In VanPatten B, Williams J (ed) Theories in Second Language Acquisition: An Introduction

Rae JW, Borgeaud S, Cai T, et al. (2021) Scaling Language Models: Methods, Analysis & Insights from Training Gopher. ArXiv, abs/2112.11446

Read J (2000) Assessing vocabulary. Cambridge University Press. https://doi.org/10.1017/CBO9780511732942

Rudner LM, Liang T (2002) Automated Essay Scoring Using Bayes’ Theorem. J. Technol., Learning and Assessment, 1 (2)

Sakoda K, Hosoi Y (2020) Accuracy and complexity of Japanese Language usage by SLA learners in different learning environments based on the analysis of I-JAS, a learners’ corpus of Japanese as L2. Math. Linguist. 32(7):403–418. https://doi.org/10.24701/mathling.32.7_403

Suzuki N (1999) Summary of survey results regarding comprehensive essay questions. Final report of “Joint Research on Comprehensive Examinations for the Aim of Evaluating Applicability to Each Specialized Field of Universities” for 1996-2000 [shōronbun sōgō mondai ni kansuru chōsa kekka no gaiyō. Heisei 8 - Heisei 12-nendo daigaku no kaku senmon bun’ya e no tekisei no hyōka o mokuteki to suru sōgō shiken no arikata ni kansuru kyōdō kenkyū’ saishū hōkoku-sho]. University Entrance Examination Section Center Research and Development Department [Daigaku nyūshi sentā kenkyū kaihatsubu], 21–32

Taghipour K, Ng HT (2016) A neural approach to automated essay scoring. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, 1–5 November, pp. 1882–1891. Association for Computational Linguistics

Takeuchi K, Ohno M, Motojin K, Taguchi M, Inada Y, Iizuka M, Abo T, Ueda H (2021) Development of essay scoring methods based on reference texts with construction of research-available Japanese essay data. In IPSJ J 62(9):1586–1604

Ure J (1971) Lexical density: A computational technique and some findings. In Coultard M (ed) Talking about Text. English Language Research, University of Birmingham, Birmingham, England

Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. In Advances in Neural Information Processing Systems, Long Beach, CA, 4–7 December, pp. 5998–6008, Curran Associates, Inc., Red Hook, NY

Watanabe H, Taira Y, Inoue Y (1988) Analysis of essay evaluation data [Shōronbun hyōka dēta no kaiseki]. Bulletin of the Faculty of Education, University of Tokyo [Tōkyōdaigaku kyōiku gakubu kiyō], Vol. 28, 143–164

Yao S, Yu D, Zhao J, et al. (2023) Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36

Zenker F, Kyle K (2021) Investigating minimum text lengths for lexical diversity indices. Assess. Writ. 47:100505. https://doi.org/10.1016/j.asw.2020.100505

Zhang Y, Warstadt A, Li X, et al. (2021) When do you need billions of words of pretraining data? Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online, pp. 1112-1125. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.90

Download references

This research was funded by National Foundation of Social Sciences (22BYY186) to Wenchao Li.

Author information

Authors and affiliations.

Department of Japanese Studies, Zhejiang University, Hangzhou, China

Department of Linguistics and Applied Linguistics, Zhejiang University, Hangzhou, China

You can also search for this author in PubMed   Google Scholar

Contributions

Wenchao Li is in charge of conceptualization, validation, formal analysis, investigation, data curation, visualization and writing the draft. Haitao Liu is in charge of supervision.

Corresponding author

Correspondence to Wenchao Li .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Ethical approval

Ethical approval was not required as the study did not involve human participants.

Informed consent

This article does not contain any studies with human participants performed by any of the authors.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplemental material file #1, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Li, W., Liu, H. Applying large language models for automated essay scoring for non-native Japanese. Humanit Soc Sci Commun 11 , 723 (2024). https://doi.org/10.1057/s41599-024-03209-9

Download citation

Received : 02 February 2024

Accepted : 16 May 2024

Published : 03 June 2024

DOI : https://doi.org/10.1057/s41599-024-03209-9

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Summer Writing Workshop: Mastering Personal Essays About Family

Cost: $395 $335

Early bird discount: Use code EARLYJUNE to take 15% off when signing up by June 7, 2024.

Some of the most impactful pieces of writing are personal essays that dive into all the complexities and nuances of family relationships. They’re also pretty much always the hardest things to write! If you want to craft compelling personal essays about your family without getting caught in the messy middle, this class is for you. This intimate five-week workshop (capped at no more than 10 students) is designed to help writers who are ready to take their essay writing to the next level and get their stories published. Instructor Kerra Bolton is an award-winning writer and filmmaker whose writing has been published on Memoir Land, Ebony, CNN.com and many other publications. Throughout the course of five weeks, writers will learn to find the most resonant ways to frame their personal essays, develop an engaging writing voice, master the art and ethics of family interviews, incorporate reflection and insight into their work and refine their essays for publication. Each 90-minute workshop is designed to polish your writing skills and push your practice forward. The first half of each class is dedicated to exploring a fundamental aspect of personal essay writing. In the second half, the group will workshop two students’ essays, providing thoughtful and constructive feedback to help you enhance your work. Over the course of five weeks, you’ll gain a deeper understanding of personal essay writing fundamentals, receive practical feedback and leave with actionable steps to get published. By the end of the class, you’ll have a polished personal essay ready for publication.

This class is right for you if…

You crave a thoughtful, supportive environment to receive feedback and improve your personal essay writing through practice and critique.

You want to publish stories that attract attention and resonate with readers.

You’re working on a memoir and want to strengthen your ability to craft smaller, focused personal essays as part of your larger project.

By the end of the class you’ll have…

A polished personal essay ready to submit to a top publication.

Writers signing up for this class must have completed a rough draft of a personal essay (1,000 to 3,000 words) by the start date. This is a workshop-based class and all students are required to read and review two other students’ essays each week.

All Narratively Academy classes are conducted online and accessible to students anywhere in the world.

Your Instructor: Kerra Bolton is an acclaimed writer and filmmaker. Her work has been featured on Memoir Land , CNN.com , CNN Español , The Times of Israel , New Worlder , Ebony and Panorama: The Journal of Intelligent Travel. She is currently working on her memoir, Water in My Bones, and her documentary film directorial debut, Return of the Black Madonna . Both projects trace her epic quest to learn to swim, dive and map sunken slave ships with Black marine archeologists. Bolton produced and starred in Detroit Rising: How the Motor City Becomes a Restorative City , released in 2020. The five-part docuseries followed Bolton as she witnessed restorative justice transform nearly every city sector during a time of racial reckoning. The series was an official selection of the San Francisco Independent Short Film Festival, was called “illuminating” by The Mercury News and won “Best Web Series” (2020) at the Cyrus International Film Festival. Bolton is also the CEO and founder of Woodbine Ventures, a transitional career coaching company.

“Kerra has such a compelling story and is full of insight and tips for students no matter where they are in their writing or research journey.” —Pia Hinkle, former student

“Kerra is a brilliant teacher, writer and person, whose guidance will take you to entirely new places.” —Jordan Rosenfeld, freelance editor and author of nine books

Registration Details: Seats in this class are limited and available on a first-come, first-serve basis. All purchases are final and nonrefundable. After signing up, you’ll receive an email receipt confirming your purchase. Prior to the start of your class you’ll receive an invitation to access the virtual classroom and view all class materials.

Questions? Email us at [email protected].

MORE: Check out all of our upcoming Narratively Academy classes here .

Sign up to get new stories and class announcements from Narratively.

• Share full article

Advertisement

Supported by

Guest Essay

I Reread a Book That Changed My Life, but I’d Changed, Too

By Margaret Renkl

Ms. Renkl is a contributing Opinion writer who covers flora, fauna, politics and culture in the American South.

On the day of the eclipse back in April, walking through Boston Common on a fine spring afternoon as every expectant face turned upward, I thought again of Annie Dillard’s wondrously dislocating essay “ Total Eclipse ,” which I have reread more times than I can count. “My hands were silver,” she wrote. “All the distant hills’ grasses were finespun metal that the wind laid down.”

Then I read “ This Is How a Robin Drinks: Essays on Urban Nature ,” the forthcoming book by the Nashville naturalist Joanna Brichetto, which begins with an epigraph from “Pilgrim at Tinker Creek,” the book that won Ms. Dillard a Pulitzer Prize when she was 29 years old: “Some unwonted, taught pride diverts us from our original intent, which is to explore the neighborhood, view the landscape, to discover at least where it is that we have been so startlingly set down, if we can’t learn why.”

And then, as if I were a dullard the universe can’t trust to take a hint, the writer Jennifer Justice mentioned in her wonderful Substack newsletter that 2024 is the 50th anniversary of the publication of “Pilgrim at Tinker Creek,” a book that changed me when I was 18 as thoroughly as the eclipse changed Annie Dillard.

On the same day, if you can believe it, the novelist Barbara Kingsolver singled out “Tinker Creek” in an Earth Day recollection for The Washington Post : “Her writing helped me see nature not as a collection of things to know or possess, but a world of conjoined lives, holy and complete, with or without me.”

Clearly it was time to read “Pilgrim at Tinker Creek” again. I first read it in 1980, gobbling up the full book after a section of it appeared in my composition textbook. I’ve been afraid to reread it ever since. When you emerge from a book entirely changed, there’s almost no chance the same transfiguration will happen again.

To reread a beloved book after a long time away is always a great risk. If it falls flat on second reading, a feeling of grief descends, as though you’d lost a beloved human and not simply a specific arrangement of words that once mattered to you for some reason you may no longer remember. To lose a book in this way feels of a kind with losing a friend.

But for a book that is more than merely a favorite, a book that has had a hand in creating you, the risk of loss is even greater. A book that is saying exactly what you desperately need to hear at a time when nothing else in your own plodding life is saying it, a book in which somehow, miraculously, every word is arranged as though to pierce your deepest heart and lodge itself there, living and whole — if you were to lose that book, you would feel that you had lost some necessary part of yourself. Or perhaps you would still have it, but it would become a phantom limb, no longer serving you except as a source of pain.

For most of my life I was an indefatigable rereader. During my decade as a high school teacher, I reread so many poems and so many lines from Shakespeare’s plays that I committed many of them to memory. I spent my summers rereading the novels I had assigned my future students to read before they arrived.

And one of the sweetest parts of parenthood was sharing treasured childhood books with my sons. Reading to them, I remembered the little girl I was, sometimes welling over with feelings too big to express, who would close the door to her room and read the ending of “Charlotte’s Web” again. The tears and the words rushed together to create a comfort I understand now in a way I could not when I was 8. Grief eases just a little when the words match the feelings, and tears are a kind of relief in any case. It is a gift when body, soul and language are of a piece for once.

Part of the pleasure of rereading a dear old book is the chance to remember who I was when I first read it and to take my own measure by standing inside its light once more. But my time for reading is rarely a matter of my own straightforward choice anymore. I read because I need to learn, or because I am eager to support the work of other writers, and I am a slow, slow reader. As the years march on, it feels almost wasteful to reread a favorite when there are so many books that I have not yet read at all. The teetering piles torment me.

The poet Camille T. Dungy reread “Tinker Creek” in 2020, as she was beginning to write “ Soil: The Story of a Black Mother’s Garden ,” a book so beautiful and moving that it is arguably Ms. Dungy’s own “Tinker Creek.” Rereading the classic text brought home to her again the sublimity of Ms. Dillard’s language, but it also raised some questions for her about the writer’s separation from the human world, her utter disengagement from the urgent issues of her day.

“Have you read it recently?” Ms. Dungy asks a colleague who declares her own love for “Pilgrim at Tinker Creek.” “You might want to.” The world has turned since 1974.

The second time around, “Tinker Creek” raised some of the same issues for me. Reading it as a 62-year-old, it turns out, is entirely different from reading it as a language-besotted college student just learning that writing like Annie Dillard’s could exist in living time, as indelible as any line by Shakespeare or Keats or Dickinson.

The features of the book that make me cast a sideways glance today — the specific circumstances of privilege, or just the good luck, that make it possible for a young woman to feel confident wandering alone in even a suburb-skirting woodland, for instance — ought to have made me cast a sideways glance in 1980, too, though they did not. I was also a young woman who knew so little of the human world that I still felt safe walking alone in the wild one.

By 1992, Ms. Dillard was dismissing her own early work as “ little, little, little books ,” but they are still magnificent to me. Rereading “Pilgrim at Tinker Creek” this spring, it was a relief to react to it in much the same way I reacted as a teenager. Reading it again, I am once more intoxicated with language, once more swept away by the violent, intertwined, unaccountable beauty of nature, deeply in love with the whole profligate living world. Reading it again, I am the girl I was then and the woman I am now. Both at once.

Margaret Renkl , a contributing Opinion writer, is the author of the books “ The Comfort of Crows: A Backyard Year, ” “ Graceland, at Last ” and “ Late Migrations .”

The Times is committed to publishing a diversity of letters to the editor. We’d like to hear what you think about this or any of our articles. Here are some tips . And here’s our email: [email protected] .

Follow the New York Times Opinion section on Facebook , Instagram , TikTok , WhatsApp , X and Threads .