[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-579033-105":59,"doc-detail-579033-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","automating-self-affirmation-essay-coding-fine-tuned-bert-performance-comparable-to-human-coders-and-comparison-with-gpt-4","Automating Self-Affirmation Essay Coding - Fine-Tuned BERT Performance Comparable to Human Coders and Comparison with GPT-4","","Automating the coding of self-affirmation essay responses supports scalable education research but is often limited by costly, time-consuming manual annotation. Fine-tuned BERT models were trained on labeled data to classify whether student writing is self-affirming, achieving strong agreement with human coders (Cohen’s Kappa ≈ 0.85) and similar performance on an external dataset (≈ 0.86). Zero-shot and few-shot GPT-4 classification produced reasonable accuracy yet did not match fine-tuned BERT, and few-shot examples did not meaningfully improve results. The model also showed consistent performance across student subgroups, including stereotype-threatened versus non-threatened groups.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/automating-self-affirmation-essay-coding-fine-tuned-bert-performance-comparable-to-human-coders-and-comparison-with-gpt-4/579033/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/automating-self-affirmation-essay-coding-fine-tuned-bert-performance-comparable-to-human-coders-and-comparison-with-gpt-4/579033.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does automated self-affirmation essay coding address?","Question",{"text":112,"@type":113},"Manual coding of student writing is labor-intensive, expensive, and can limit large-scale studies. Automation aims to replace or augment human coders for identifying self-affirming content.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the fine-tuned BERT model perform compared with human coders?",{"text":117,"@type":113},"The fine-tuned BERT model achieves comparable performance to human coders, with Cohen’s Kappa around 0.85 on the original comparison and about 0.86 on an external dataset.",{"name":119,"@type":110,"acceptedAnswer":120},"How does GPT-4 classification compare to the fine-tuned BERT approach?",{"text":121,"@type":113},"GPT-4 zero-shot predictions provide reasonable accuracy but do not reach the fine-tuned BERT model’s performance or human-level agreement, and few-shot prompting does not substantially improve results.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},579033,1792161997,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Automating Self-Affirmation Essay Coding: Fine-Tuned BERT Performance Comparable to Human Coders and Comparison with GPT-4  \nCong Ye  \nAmerican Institutes for Research Arlington, Virginia, USA[cye@air.org](cye@air.org)  \nTrisha H. Borman American Institutes for Research Arlington, Virginia, USA  \n[tborman@air.org](tborman@air.org)  \nGeoffrey D. Borman Arizona State University Tempe, Arizona, USA [gborman@asu.edu](gborman@asu.edu)  \nPrevious studies have demonstrated that a self-affirmation writing intervention, in which students reflect on personally important values, positively impacts students’ school performance, and there is active research on this intervention. However, this research requires manual coding of students’ writing exercises, and this manual coding has proved to be a time-consuming and expensive undertaking. To assist future selfaffirmation intervention studies or educators implementing the writing exercise, we employed our labeled data to fine-tune a pre-trained language model that achieves a comparable level of performance to that of human coders (Cohen’s Kappa: 0.85 between machine coding and human coders as compared to 0.83 between human coders). To explore the potential of more advanced language models without requiring a large training dataset, we also evaluated OpenAI’s GPT-4 in a zero-shot and few-shot classification setting. GPT-4’s zeroshot predictions yield reasonable accuracy but do not reach the fine-tuned BERT model’s performance or human-level agreement. Adding example essays (few-shot prompting) did not appreciably improve GPT-4’s results. Our analysis also finds that the BERT model’s performance is consistent across student subgroups, with minimal disparity between “stereotype-threatened” and “non-threatened” students, which are the focal groups for comparison in the self-affirmation intervention. We further demonstrate the generalizability of the fine-tuned model on an external dataset collected by a different research team: the model maintained a high agreement with human coders (Cohen’s Kappa = 0.86) on this new sample. These results suggest that a finetuned transformer model can reliably code self-affirmation essays, thereby reducing the coding burden for future researchers and educators. We make the fine-tuned model publicly available to help the research community automate the burdensome task of coding at [https://github.com/visortown/bert-self-affirm](https://github.com/visortown/bert-self-affirm)  \n[Keywords:](Keywords: BERT fine-tuning)[ BERT fine-tuning](Keywords: BERT fine-tuning), GPT-4, text classification, self-affirmation intervention, student writing coding, automated essay classification  \n66 Journal of Educational Data Mining, Volume 18, No 1, 2026  \n1. INTRODUCTION  \nStereotype threat refers to the psychological phenomenon in which individuals experience anxiety or underperformance when confronted with a stereotype that is relevant to their social identity (Steele and Aronson, 1995) . This phenomenon has been shown to significantly impact academic performance, particularly among marginalized groups. One effective intervention to combat stereotype threat is to have students write exercises that affirm their important beliefs and values (Steele and Liu, 1983; Liu and Steele, 1986), which helps students reflect on positive aspects of their identity to buffer them from the stereotype threat. More recent research has highlighted the efficacy of interventions designed to mitigate the adverse effects of stereotype threat. For instance, value-affirmation exercises, which involve students reflecting on their core beliefs and values, have been demonstrated to buffer against stereotype threat by reinforcing positive aspects of identity (Cohen et al., 2006; Liu et al., 2021; Sherman et al., 2013) . These interventions have been particularly effective in educational settings, where they have been shown to reduce achievement gaps and improve long-term academic outcomes (Borman et al., 201","cbCaisPx673TkdJ2","https://ap.wps.com/l/cbCaisPx673TkdJ2","pdf",348584,23,"English","# Introduction\n## Background on stereotype threat and self-affirmation writing\n## Why manual coding is a bottleneck\n## Prior NLP work and the need for automated classification\n## Study motivation from advances in pre-trained language models","[{\"question\":\"What problem does automated self-affirmation essay coding address?\",\"answer\":\"Manual coding of student writing is labor-intensive, expensive, and can limit large-scale studies. Automation aims to replace or augment human coders for identifying self-affirming content.\"},{\"question\":\"How does the fine-tuned BERT model perform compared with human coders?\",\"answer\":\"The fine-tuned BERT model achieves comparable performance to human coders, with Cohen’s Kappa around 0.85 on the original comparison and about 0.86 on an external dataset.\"},{\"question\":\"How does GPT-4 classification compare to the fine-tuned BERT approach?\",\"answer\":\"GPT-4 zero-shot predictions provide reasonable accuracy but do not reach the fine-tuned BERT model’s performance or human-level agreement, and few-shot prompting does not substantially improve results.\"}]","Automating Self-Affirmation Essay Coding - Fine-Tuned BERT Performance Comparable to Human Coders and Comparison with GPT-4 | PDF",1792034875,58]