[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-579250-105":59,"doc-detail-579250-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","a-survey-of-graph-based-knowledge-tracing-models-applications-and-future-directions","A Survey of Graph-Based Knowledge Tracing - Models, Applications, and Future Directions","","Knowledge Tracing (KT) is central to intelligent education by predicting students’ next performance from their interaction histories. This survey examines Graph-based Knowledge Tracing (GbKT), which uses graph neural networks to explicitly model many-to-many structural relations among students, exercises, and knowledge components. It proposes a two-dimensional taxonomy, unifies model training via message-passing perspectives, analyzes application-driven interpretability and intervention, evaluates 17 public datasets, and outlines future GbKT research directions.",{"@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/a-survey-of-graph-based-knowledge-tracing-models-applications-and-future-directions/579250/",{"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/a-survey-of-graph-based-knowledge-tracing-models-applications-and-future-directions/579250.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","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 is Knowledge Tracing (KT) and what does it predict?","Question",{"text":112,"@type":113},"KT tracks a student’s knowledge state through interaction records and predicts the probability of the student performing correctly on the next exercise.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does Graph-based Knowledge Tracing (GbKT) differ from sequential KT models?",{"text":117,"@type":113},"GbKT leverages graph neural networks to explicitly represent structural many-to-many relationships and prerequisite-like dependencies between exercises and knowledge components, enabling improved interpretability and intervention.",{"name":119,"@type":110,"acceptedAnswer":120},"What does the survey contribute for researchers using GbKT datasets?",{"text":121,"@type":113},"It systematically evaluates 17 public datasets and provides guidance for dataset selection.","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},579250,1792172266,{"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},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","A Survey of Graph-Based Knowledge Tracing from Structural and Propagation Perspectives: Models, Applications, and Future Directions  \nMeiling Xu University of Turku Turku, Finland [meilxu@utu.fi](meilxu@utu.fi)  \nJanne Kujala University of Turku Turku, Finland [janne.kujala@utu.fi](janne.kujala@utu.fi)  \nJari Metsmuuronen University of Turku  \nTurku, Finland [jari.metsamuuronen@gmail.com](jari.metsamuuronen@gmail.com)  \nMikko-Jussi Laakso University of Turku Turku, Finland [milaak@utu.fi](milaak@utu.fi)  \nKnowledge Tracing (KT) is a fundamental task in intelligent education that tracks students’ knowledge states through their historical interactions. Early deep learning-based KT mainly relies on sequential models, which often find it more challenging to explicitly model the complex many-to-many relationships between students and knowledge entities, such as exercises and knowledge components. Graphbased Knowledge Tracing (GbKT) further leverages graph neural networks to explicitly represent these structural relationships, creating new opportunities for learning-state monitoring and personalized intervention. In this survey, we conduct an in-depth exploration of recent progress in GbKT research. First, we introduce a two-dimensional taxonomy that aligns the primary modeling motivations with graph structural forms, and we characterize them with unified message-passing equations. Second, focusing on applications, such as the discovery of knowledge structures, modeling with educational psychology theories and interpretability, and personalized recommendation and path planning, we show how graph semantics endow the models with new interpretability and intervention capabilities. Third, we systematically evaluate 17 public datasets, offering researchers guidance on dataset selection. Finally, we outline promising future research directions for GbKT.  \nKeywords: knowledge tracing, graph-based knowledge tracing, graph neural networks, student modeling, educational data mining, personalized learning  \n1. INTRODUCTION  \nIn AI-driven online learning environments, Knowledge Tracing (KT) (Corbett and Anderson, 1994) is a key task, aiming to accurately predict students’ performance on the next exercise on the basis of their interaction records with previous exercises (Dowling and Hockemeyer, 2001;  \n41 Journal of Educational Data Mining, Volume 18, No 2, 2026  \nFigure 1: An illustration of the KT scenario.  \nPardos et al., 2013) . In recent years, deep learning models—such as Deep Knowledge Tracing (DKT) and attention-based KT models—have been shown to significantly outperform traditional methods in terms of prediction accuracy (Piech et al., 2015 ; Choi et al., 2020 ; Shin et al., 2021) .  \nFigure 1 illustrates a common approach in traditional KT: a student’s exercise–response sequence is modeled as a time series to incrementally infer knowledge mastery. Student A answers four exercises, e 1–e4 , at time steps t1–t4. Each exercise is linked to knowledge components (KC) c 1–c4. At t 1–t3 , the responses are observed as “correct” or “incorrect”, allowing the model to update mastery of the related KCs. At t4 , the outcome of e4 is still unknown (denoted “?”) . The model therefore predicts the probability that the student will solve e4 correctly, using the prior response sequence and the dependencies among KCs.  \nBayesian Knowledge Tracing (BKT) (Corbett and Anderson, 1994) is the foundational model in the knowledge tracing field. BKT is based on a Hidden Markov Model and uses four probability parameters—initial mastery probability, learning probability, guess probability, and slip probability—to independently model each knowledge component. It updates the mastery probability estimate via Bayesian inference after each student response and has been widely deployed in intelligent tutoring systems such as Cognitive Tutor and MATHia. Notably, BKT remains an active research direction, with recent advances in interpretability (Zhou et al., 2024), para","cbCaiomyNXftAsDz","https://ap.wps.com/l/cbCaiomyNXftAsDz","pdf",1111607,47,"English","# Introduction\n## Knowledge Tracing overview\n## Bayesian Knowledge Tracing (BKT)\n## Deep Learning Knowledge Tracing (DLKT)\n## Limitations of sequential models\n## Motivation for graph-based approaches","[{\"question\":\"What is Knowledge Tracing (KT) and what does it predict?\",\"answer\":\"KT tracks a student’s knowledge state through interaction records and predicts the probability of the student performing correctly on the next exercise.\"},{\"question\":\"How does Graph-based Knowledge Tracing (GbKT) differ from sequential KT models?\",\"answer\":\"GbKT leverages graph neural networks to explicitly represent structural many-to-many relationships and prerequisite-like dependencies between exercises and knowledge components, enabling improved interpretability and intervention.\"},{\"question\":\"What does the survey contribute for researchers using GbKT datasets?\",\"answer\":\"It systematically evaluates 17 public datasets and provides guidance for dataset selection.\"}]","A Survey of Graph-Based Knowledge Tracing - Models, Applications, and Future Directions | PDF",1792035285,118]