日本データベース学会の皆様 京都工芸繊維大学のDuanです。 2026年11月13日〜15日に香港で開催されるデータマイニングに関する国際会議ADMA2026におけるSpecial Session "Educational Data Mining in the Era of Large Language Models (EDM-LLM)" につきまして、ご案内申し上げます。 ぜひ投稿をご検討いただければ幸いです。 何卒よろしくお願い申し上げます。 +++ General Information +++ The 22nd International Conference on Advanced Data Mining and Applications 2026 Special Session: Educational Data Mining in the Era of Large Language Models (EDM-LLM) 13th ~ 15th November, 2026 Hong Kong https://adma2026.github.io/ +++ Important Dates +++ - Full/Poster Paper submission: June 26, 2026 - Acceptance notification: August 21, 2026 - Camera-ready papers submission: September 4, 2026 - Conference Dates: November 13-15, 2026 +++ Aims and Scope +++ Educational Data Mining lies at the intersection of data mining, machine learning, the learning sciences, and educational technology. This special session aims to provide a focused forum within ADMA2026 for research on how advanced data mining methods can be used to understand learning processes, support teachers and learners, personalize instruction, and examine the growing role of large language models in educational settings. The session welcomes methodological papers, application papers, benchmark studies, system papers, and reports of industrial practice. It is intended both for work that uses educational data to motivate advances in data mining and for work that applies state of-the-art data mining methods to  important educational problems. In particular, the session aims to connect the broader data mining community with real educational challenges involving sequential, relational, textual, code-based, and multimodal data. +++ Topics +++ The special session will cover, but are not limited to: - Learner knowledge and performance modeling, knowledge tracing, mastery estimation, and academic risk prediction; - Domain knowledge modeling, prerequisite discovery, knowledge component discovery, and graph/sequence mining of learning processes; - Educational recommenders, instructional sequencing, intervention optimization, and reinforcement learning for adaptive learning; - Multimodal learning analytics using logs, text, code, speech, video, eye-tracking, or classroom interaction data; - Social and collaborative learning analytics, peer learning, discussion/forum mining, and group interaction modeling; - Open-ended assessment, automated grading, writing and code analytics, peer review modeling, and educational feedback generation; - LLM applications in EDM, including intelligent tutoring, hint generation, question generation, feedback synthesis, knowledge component extraction, item difficulty estimation, and classroom support; - Evaluation of LLMs in education, human-AI comparison, benchmarking against student performance, and studies of AI-assisted learning behaviors; - Data resources, benchmarks, and cross-platform or cross-institutional studies for educational data mining. +++ Publication +++ Accepted papers will be published by Springer in their Lecture Notes in Artificial Intelligence (LNAI) and indexed in EI and DBLP. +++ Submission Instructions +++ Manuscripts must be prepared in accordance with the LNAI format and should not exceed 15 pages.  For the template and details on the LNAI style, please check the following website: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-gu… Papers will go through a full peer review process in a double-blind manner. Submission site: https://cmt3.research.microsoft.com/ADMA2026 +++ Special Session Chair +++ - Weining Qian, East China Normal University, China - Yun Liu, Kyoto Institute of Technology, Japan - Yijun Duan, Kyoto Institute of Technology, Japan