[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-582154-105":3,"doc-detail-582154-en":80,"detail-sidebar-cat-0-en-105":98},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","enhancing-chatgpt-based-writing-research-through-effective-prompt-use-issues","Enhancing ChatGPT-Based Writing Research Through Effective Prompt Use - Issues","","This article examines how prompt use affects the validity and reliability of ChatGPT outputs in written assessment and feedback, with a specific focus on detecting logical fallacies in student essays. Using a case study design, it compares outputs from repeated iterations of a carefully designed prompt across new conversation windows against a single-shot prompt followed by follow-up prompts. Findings indicate that combining multiple prompt iterations can improve precision and accuracy, while excessive follow-ups may reduce validity. The work proposes pilot-and-tailor guidance for researchers and teachers.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/enhancing-chatgpt-based-writing-research-through-effective-prompt-use-issues/582154/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/enhancing-chatgpt-based-writing-research-through-effective-prompt-use-issues/582154.png","ImageObject",300,407,{"name":42,"@type":43},"Ophelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-09","2026-10-15",true,{"@type":52,"interactionType":53,"userInteractionCount":33},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"How does prompt iteration across new conversation windows affect fallacy detection?","Question",{"text":62,"@type":63},"Combining outputs from multiple iterations of the same prompt can enhance precision and accuracy in identifying logical fallacies.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"What role do follow-up prompts play in ChatGPT-based analysis?",{"text":67,"@type":63},"Follow-up prompts can produce a more exhaustive analysis, though excessive follow-ups create a risk of diminishing validity.",{"name":69,"@type":60,"acceptedAnswer":70},"Why is systematic piloting and tailoring of prompts recommended?",{"text":71,"@type":63},"To improve the validity and reliability of generative-AI outputs, researchers and teachers should adapt prompt use to their specific research contexts and task needs.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},582154,1792811605,{"code":4,"msg":81,"data":82},"success",{"doc_id":78,"user_id":83,"nickname":42,"user_avatar":84,"doc_module":4,"category_id":85,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":86,"file_id":87,"file_url":88,"file_type":89,"file_size":90,"view_count":33,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":91,"language":92,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":93,"faqs":94,"seo_title":95,"seo_description":12,"update_tm":96,"read_time":97,"preview_page_count":4},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"ISSUES  \nEnhancing ChatGPT-Based Writing Research Through Effective Prompt Use  \nNeil E. J. A. Bowen1, Richard Watson Todd2  \n1 English Department, Thammasat University, 2 School of Liberal Arts, King Mongkut’s University of Technology Thonburi  \nKeywords: prompting generative AI, AI-based written feedback, iterative prompts, follow-up prompts, ChatGPT output consistency  \n[https://doi.org/10.56297/vaca6841/OZFH1876/SFKW4394](https://doi.org/10.56297/vaca6841/OZFH1876/SFKW4394)  \nTeaching English with Technology Vol. 25, Issue 1, 2025  \nAn increasing number of studies have investigated how ChatGPT can aid in written assessment and feedback provision. However, many studies overlook its conversational design and underlying architecture, raising concerns about the reliability and validity of their analytical outputs. Therefore, applying first principles thinking to prompt use, and through a case study approach, we explore some of the challenges in using ChatGPT to identify logical fallacies in student essays. Specifically, we examine the outputs from two kinds of interactions: (1) multiple iterations of a carefully designed prompt across new conversation windows, and (2) a single-shot application of the designed prompt followed by two rounds of follow-up prompts. Results show that combining outputs from multiple iterations of the same prompt can enhance precision and accuracy, and that follow-up prompts can generate a more exhaustive analysis, but there is also a risk of diminishing validity with excessive follow-ups.  \nTherefore, to increase the validity and reliability of generative-AI outputs, we argue that in addition to rigorous prompt design, researchers and teachers need to systematically pilot and tailor the use of prompts to their specific research contexts or task needs. With this in mind, we provide some preliminary guidelines for prompt use.  \n1. Introduction  \nWith increasing acceptance of the use of generative artificial intelligence (GenAI) as a tool to aid student writers, research into the validity and reliability of GenAI feedback is a growing necessity. One key area where more research is needed concerns prompt use. Therefore, in this paper, based on problems we encountered while using ChatGPT to analyse reasoning fallacies in student essays, and considering the limitations imposed by ChatGPT’s underlying architecture, we apply first principles thinking to prompt use. Our goal is not to add to the literature on prompt design, but to propose some procedures for prompt use.  \nMoreover, we argue that such procedures are essential not just for researchers wishing to investigate the validity and reliability of GenAI models as support tools for teaching writing, but also for teachers and students. For instance, the ability to accurately detect reasoning fallacies is integral to critical thinking, which is a key learning outcome in teaching English to speakers of other  \nlanguages (TESOL) (Atkinson, 1997; Davidson & Dunham, 1997) . Specifically, when writers can identify and correct logical fallacies in their own and others’ writing, they engage more deeply with metacognitive processes and improve overall argumentative coherence (Hyland, 2003; Wingate, 2012) . Teachers seeking practical strategies to enhance critical thinking and analytical skills can leverage ChatGPT to pinpoint common reasoning errors, providing immediate, targeted feedback to students (Ferris, 2010; Hyland & Hyland, 2006) . However, due to ChatGPT’s inherent variability and conversational nature (OpenAI, 2022), single-shot prompts may fail to capture all relevant fallacies consistently. Consequently, exploring multiple iterations and followup prompting strategies becomes essential to reliably support learners’noticing and correcting fallacious reasoning, ultimately strengthening their writing competence and critical awareness.  \n1.1. Writing and using prompts  \nWhile GenAI has various educational uses, teachers and researchers have shown particular","cbCailr6w6BlyTs9","https://ap.wps.com/l/cbCailr6w6BlyTs9","pdf",220517,15,"English","# Introduction\n## Writing and using prompts","[{\"question\":\"How does prompt iteration across new conversation windows affect fallacy detection?\",\"answer\":\"Combining outputs from multiple iterations of the same prompt can enhance precision and accuracy in identifying logical fallacies.\"},{\"question\":\"What role do follow-up prompts play in ChatGPT-based analysis?\",\"answer\":\"Follow-up prompts can produce a more exhaustive analysis, though excessive follow-ups create a risk of diminishing validity.\"},{\"question\":\"Why is systematic piloting and tailoring of prompts recommended?\",\"answer\":\"To improve the validity and reliability of generative-AI outputs, researchers and teachers should adapt prompt use to their specific research contexts and task needs.\"}]","Enhancing ChatGPT-Based Writing Research Through Effective Prompt Use - Issues | PDF",1792042724,38,{"code":4,"msg":81,"data":99},[100,104,108,112,117,122,127,130,135,138,142],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},5,"Comic",60,"comic",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},6,"Technology",50,"technology",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":125,"slug":126},7,"Healthcare",40,"healthcare",{"id":85,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":128,"slug":129},30,"research-report",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":133,"slug":134},9,"Religion & Spirituality",20,"religion-spirituality",{"id":133,"doc_module":4,"doc_module_name":25,"category_name":136,"show_sort_weight":133,"slug":137},"World Cup","world-cup",{"id":139,"doc_module":4,"doc_module_name":25,"category_name":140,"show_sort_weight":139,"slug":141},10,"Lifestyle","lifestyle",{"id":143,"doc_module":4,"doc_module_name":25,"category_name":144,"show_sort_weight":113,"slug":145},19,"General","general"]