[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-577875-105":59,"doc-detail-577875-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","statistical-and-qualitative-analysis-of-chatgpt-and-human-raters-in-preservice-teachers-writing-assessment","Statistical and Qualitative Analysis of ChatGPT and Human Raters in Preservice Teachers’ Writing Assessment","","Teachers spend considerable time producing feedback, making writing assessment both labor-intensive and time-sensitive. This qualitative study compared expert raters’ and ChatGPT’s assessments and feedback on Turkish undergraduate students’ written assignments using a rubric covering content, language use, vocabulary, organization, and mechanics. Three experts and ChatGPT graded 14 papers, provided justifications, and scores were examined with intraclass correlation to evaluate consistency. Feedback was analyzed to identify strengths, weaknesses, and preference for constructive, supportive guidance, revealing moderate-to-weak agreement on subscales but better reliability in total scores.",{"@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/statistical-and-qualitative-analysis-of-chatgpt-and-human-raters-in-preservice-teachers-writing-assessment/577875/",{"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/statistical-and-qualitative-analysis-of-chatgpt-and-human-raters-in-preservice-teachers-writing-assessment/577875.png","ImageObject",300,407,{"name":92,"@type":93},"Emma Wilson","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What was the study designed to compare?","Question",{"text":112,"@type":113},"The study compared expert raters’ evaluations and feedback with ChatGPT’s assessments of written texts, focusing on suitability for writing skill assessment.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were the students’ assignments evaluated?",{"text":117,"@type":113},"Three experts and ChatGPT graded 14 Turkish undergraduate assignments using a rubric covering content, language use, vocabulary, organization, and mechanics, and each decision was justified.",{"name":119,"@type":110,"acceptedAnswer":120},"What differences did the study find between experts and ChatGPT?",{"text":121,"@type":113},"Experts performed better in explanatory feedback, interpretation, and experience, while ChatGPT excelled in automation and continuity and data processing capacity; experts showed weaknesses in limited time/energy and comparison bias, while ChatGPT showed ambiguous expressions and repetition.","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},577875,1792188783,{"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":34,"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},3848291630094,"https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Statistical and qualitative analysis of ChatGPT and human raters in preservice teachers’ writing assessment  \nBahadır Gülden1, Huzeyfe Bilge2*, Pınar Kanık Uysal3  \n1Bayburt University, Faculty of Education, Department of Turkish Language Education, Bayburt, Türkiye 2Kafkas University, Faculty of Education, Department of Turkish Language Education, Kars, Türkiye 3Ordu University, Faculty of Education, Department of Turkish Language Education, Ordu, Türkiye  \nARTICLE HISTORY  \nReceived: Apr. 17, 2025  \nAccepted: Nov. 9, 2025  \nKEYWORDS  \nArtificial Intelligence, ChatGPT,  \nWriting feedback, Human-raters.  \nAbstract: Teachers spend a significant amount of time providing feedback. This study compared expert and ChatGPT assessments and feedback on written texts to determine the suitability of AI for writing skill assessments that are time-consuming to assess and provide feedback. Three experts and ChatGPT graded 14 Turkish undergraduate students’ assignments using rubric that included content, language use, vocabulary, organization, and mechanics, and justified their decisions. The study involved document review and triangulation, a qualitative design. In addition, an intraclass correlation coefficient was used to assess the consistency of the ChatGPT and the experts’ scores. All feedback was qualitatively analyzed to identify the strengths and weaknesses of the experts and their similarities with ChatGPT. Experts and ChatGPT had moderate to weak consistency in the writing subscales, while good reliability was found in the total score. Experts excelled in ‘explanatory feedback’,‘interpretation’ and ‘experience’, while ChatGPT excelled in ‘automation and continuity’ and ‘data processing capacity’. Experts’ weaknesses included ‘limited time and energy’ and ‘comparison bias’, while ChatGPT’s weaknesses were‘ambiguous expressions’ and ‘repetition’. The study also found that experts and ChatGPT preferred to provide constructive and supportive feedback.  \nINTRODUCTION  \nAssessment is a crucial component of language teaching, as it provides valuable information about learners’ progress and guides instructional decisions. For assessments to be effective, they should be both feasible and reliable (McMillan, 2018) . In language classes, developing writing skills often requires assessment formats that allow for richer, more authentic responses, most notably, open-ended questions. These questions can offer advantages over closed-ended formats by enabling students to demonstrate higher-order thinking and language production skills. However, despite their potential, open-ended questions make up only 24% of language teachers’ question sets (Kanık Uysal et al., 2022), partly because they require more time to prepare, administer, and evaluate. Open-ended writing assessments can take 15-20 minutes per student (Wang et al., 2024), which may require teachers to work outside of school hours. Providing feedback to students is crucial for their learning. However, teachers struggle to  \n*Corresponding author at: Huzeyfe BİLGE 􀀍 [hbilge2@gmail.com](hbilge2@gmail.com) 􀁽 Kafkas University, Faculty of Education, Department of Turkish Language Education, Kars, Türkiye  \nThe copyright of the published article belongs to its author under CC BY 4.0 license. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/)  \n[e-ISSN: 2148-7456](e-ISSN: 2148-7456)  \nmanage such a workload due to time constraints. According to a global study, teachers spend 25 hours a week on non-student responsibilities, including assessment and feedback (Bryant et al., 2020). For teachers who even struggle to follow the curriculum (Akaya & Kurtuluş, 2011), it is difficult to assess writing skills and provide feedback using open-ended questions. This can lead to students being deprived of feedback that is vital for their learning. In addition to the time-consuming evaluation of open-ended questions, teachers also give ","cbCaikWTKIbqxykM","https://ap.wps.com/l/cbCaikWTKIbqxykM","pdf",620856,22,"English","# Introduction\n## Assessment and writing feedback challenges\n## Open-ended questions and reliability issues\n## AI-based support for time constraints\n# Method and analysis approach\n## Qualitative design and triangulation\n## Rubric-based scoring and justification\n## Consistency measurement and qualitative feedback coding","[{\"question\":\"What was the study designed to compare?\",\"answer\":\"The study compared expert raters’ evaluations and feedback with ChatGPT’s assessments of written texts, focusing on suitability for writing skill assessment.\"},{\"question\":\"How were the students’ assignments evaluated?\",\"answer\":\"Three experts and ChatGPT graded 14 Turkish undergraduate assignments using a rubric covering content, language use, vocabulary, organization, and mechanics, and each decision was justified.\"},{\"question\":\"What differences did the study find between experts and ChatGPT?\",\"answer\":\"Experts performed better in explanatory feedback, interpretation, and experience, while ChatGPT excelled in automation and continuity and data processing capacity; experts showed weaknesses in limited time/energy and comparison bias, while ChatGPT showed ambiguous expressions and repetition.\"}]","Statistical and Qualitative Analysis of ChatGPT and Human Raters in Preservice Teachers’ Writing Assessment | PDF",1792032581,55]