[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-577095-105":59,"doc-detail-577095-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","two-voices-one-draft-a-diachronic-comparison-of-human-and-ai-feedback-in-efl-essay-writing","Two voices, one draft - a diachronic comparison of human and AI feedback in EFL essay writing","","As intelligent technological tools increasingly permeate educational contexts, chatbots have emerged as prominent aids in language learning. This study investigates the comparative effectiveness of human- and AI-generated feedback on EFL learners’ essay writing, comparing feedback focus, specificity, and rubric alignment. Using a diachronic perspective and GPT-4 post hoc feedback on baseline drafts, results show partial alignment on local grammar issues but clearer qualitative divergence on higher-order, meaning-level concerns.",{"@graph":69,"@context":123},[70,84,106],{"@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/two-voices-one-draft-a-diachronic-comparison-of-human-and-ai-feedback-in-efl-essay-writing/577095/",{"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/two-voices-one-draft-a-diachronic-comparison-of-human-and-ai-feedback-in-efl-essay-writing/577095.png","ImageObject",300,407,{"name":92,"@type":93},"Finn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What does the study compare in EFL essay writing?","Question",{"text":113,"@type":114},"It compares human instructor feedback and generative AI feedback (GPT-4) on learners’ essay writing, focusing on feedback focus, specificity, and alignment with rubric categories.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is GPT-4 feedback used in the research design?",{"text":118,"@type":114},"GPT-4 generates feedback on students’ initial drafts retrospectively for analytic comparison only; students do not receive or use AI feedback during revision.",{"name":120,"@type":111,"acceptedAnswer":121},"What are the main findings about similarities and differences?",{"text":122,"@type":114},"There is partial alignment between GPT-4 and instructor feedback, especially for local issues like grammatical accuracy and sentence-level clarity. However, qualitative comparisons show divergence on higher-order concerns such as task fulfilment, rhetorical appropriacy, and content elaboration.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},577095,1792192053,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":26,"preview_page_count":4},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","Australian Journal of Applied Linguistics ISSN 2209-0959  \n[https://www.castledown.com/journals/ajal/](https://www.castledown.com/journals/ajal/)  \nAustralian Journal of Applied Linguistics, 9, 103200 (2026)  \n[https://doi.org/10.29140/ajal.2026.103200](https://doi.org/10.29140/ajal.2026.103200)  \nTwo voices, one draft: a diachronic comparison of human and AI feedback in EFL essay writing  \nSZU-YU RUBY CHEN   \nChung Yuan Christian University, Taiwan  \nAbstract  \nAs intelligent technological tools increasingly permeate educational contexts, chatbots have emerged as prominent aids in language learning. This study investigates the comparative effectiveness of human-and AI-generated feedback on EFL learners’ essay writing, focusing on differences and similarities in feedback focus, specificity, and rubric alignment. Specifically, the study examines how feedback from a human instructor and a generative AI (GenAI) system, GPT-4, varies across three dimensions: structure and organisation, content and ideas, and grammar. A diachronic perspective is used to analyse students’ observed revision development across drafts under instructor feedback, alongside a post hoc comparison of GPT-4 feedback applied to the same baseline texts.  \nParticipants were twenty-six EFL college students enrolled in an English composition course. The study focused on the production of comparison essays through a threestage process. In the first stage, students independently wrote their initial drafts at home, with access to dictionaries or online resources but without direct assistance. In the second stage, the drafts received written feedback from a human instructor. In the third stage, GPT-4 generated feedback on students’ initial drafts retrospectively for analytic comparison only; students did not receive or use AI feedback during revision. Instructor scores and GPT-4 scores were derived using the same rubric categories to enable controlled comparison. Findings show partial alignment between GPT-4 and instructor feedback, particularly in identifying recurring local issues such as grammatical accuracy and sentence-level clarity. However, qualitative comparisons indicate clearer divergence on higher-order concerns. For example, instructor feedback provided richer, context-sensitive guidance related to task fulfilment, rhetorical appropriacy, and content elaboration, whereas GPT-4 feedback was more standardised and rubric-driven, often foregrounding surface-level edits and general recommendations.  \nCopyright © 2026 Szu-Yu Ruby Chen  \nThese results underscore the potential value of integrating GenAI tools into EFL writing instruction while also highlighting current limitations. Pedagogically, the findings support blended feedback models in which AI supplements rapid local editing and initial diagnostic support, while teachers provide meaning-level guidance and mediate feedback uptake. The study contributes to a deeper understanding of how human and AI feedback may complement each other and offers pedagogical insights into the thoughtful use of AI in academic writing contexts.  \nKeywords: EFL writing, human-/AI-feedback, diachronic revision analysis  \nIntroduction  \nBackground of the Research  \nIn recent decades, there has been a growing interest in the integration of technology, ushering in a new era in the field of pedagogy. Web-based platforms, in particular, have gained widespread popularity as valuable tools in language teaching and learning. The increasing adoption of web-based platforms by researchers in classrooms raises an important issue for educators, i.e. the effective incorporation of technological tools into language pedagogy. As technology becomes an integral part of educational settings, the use of chatbots as a learning assistant is garnering increased attention. This extends to various contexts, including first language acquisition, second language learning, and foreign language education. Chatbots, particularly those powered by generative ar","cbCaikQ4KxyMcSwb","https://ap.wps.com/l/cbCaikQ4KxyMcSwb","pdf",562686,24,"English","# Introduction\n## Background of the Research","[{\"question\":\"What does the study compare in EFL essay writing?\",\"answer\":\"It compares human instructor feedback and generative AI feedback (GPT-4) on learners’ essay writing, focusing on feedback focus, specificity, and alignment with rubric categories.\"},{\"question\":\"How is GPT-4 feedback used in the research design?\",\"answer\":\"GPT-4 generates feedback on students’ initial drafts retrospectively for analytic comparison only; students do not receive or use AI feedback during revision.\"},{\"question\":\"What are the main findings about similarities and differences?\",\"answer\":\"There is partial alignment between GPT-4 and instructor feedback, especially for local issues like grammatical accuracy and sentence-level clarity. However, qualitative comparisons show divergence on higher-order concerns such as task fulfilment, rhetorical appropriacy, and content elaboration.\"}]","Two voices, one draft - a diachronic comparison of human and AI feedback in EFL essay writing | PDF",1792031035]