Panel Session

Panelist 1. Prof.  Looi Chee Kit, Education University of Hong Kong, Hong Kong

Bio: Professor Looi Chee Kit is Chair Professor of Learning Sciences at the Education University of Hong Kong. He is also Emeritus Professor at National Institute of Education (NIE) of Nanyang Technological University (NTU). His research lies at the intersection of the learning sciences and educational technology, with a particular focus on technology-enhanced learning, computer-supported collaborative learning, mobile learning and learning analytics. In recent years, Professor Looi has also been actively engaged in exploring the integration of Artificial Intelligence (AI) in education. He is a Fellow of the International Society of Learning Sciences, and a Fellow of the Asia-Pacific Society for Computers in Education. He was the founding member of the Global Chinese Society of Computers in Education, and served as its President (2017-2019).

Panelist 2. Prof. Cheng-Hsuan Li, National Taichung University of Education, Taiwan

Bio: Professor Li is a distinguished scholar in the fields of pattern recognition, machine learning, and educational measurement. He currently serves as a professor at the Graduate Institute of Educational Information and Measurement at National Taichung University of Education. His research encompasses areas such as hyperspectral image analysis, cognitive diagnosis models, and collaborative problem-solving assessment. He previously served as the Director General of the Department of Information and Technology Education at the Ministry of Education. He is currently the principal investigator of the Educational Big Data Analytics Project funded by Taiwan’s Ministry of Education.

Title: Data-Driven Evolution of the Taiwan Adaptive Learning Platform (TALP): From Prompt Engineering, Cognitive Diagnosis to the IRT-Oriented "TALPer" AI Learning Partners

Abstract: Since 2022, Taiwan has implemented the Digital Learning Enhancement Plan for K-12 Education, a four-year national initiative with a NT$20 billion budget. It focuses on three pillars: enriching digital learning content, ensuring universal access through mobile devices and wireless networks, and establishing a national educational big data infrastructure. At the heart of this strategy is the Taiwan Adaptive Learning Platform (TALP), the central engine for personalized learning. TALP integrates knowledge structure mapping with the KSAT cognitive diagnosis model to precisely identify error types and generate individualized learning paths. Its Four Basic Lesson Sessions, grounded in socially shared regulation of learning, enable teachers to scaffold technology-enhanced self-regulated learning in classrooms. In 2024, TALP entered a new phase with the integration of Large Language Models (LLMs), giving rise to the Prompt-Oriented TALPer. This marks a significant shift from diagnostic AI—focused on analyzing learner errors—to generative AI that actively supports learning through adaptive prompts, interactive dialogues, and context-aware feedback. The emerging TALPer ecosystem integrates multiple models: KSAT for fine-grained cognitive diagnosis and, in the next phase, Item Response Theory (IRT) for generating high-quality assessment items. Combined with LLM-based generative capabilities, TALPer will evolve into a suite of AI learning partners with differentiated functions, enabling richer forms of personalized and collaborative learning. At the governance level, learner behavior data from TALP will feed into the national Educational Big Data Repository. Combined with cross-platform analytics, this infrastructure will inform remedial learning strategies, mitigate challenges such as summer learning loss, and transform platform clickstream data into a reliable evidence base for shaping national education policy.

Panelist 3. Prof. Ting-Chia Hsu, Distinguished Professor in National Taiwan Normal University, Taiwan

Bio: Professor Hsu is a leading scholar in educational technology, with research interests encompassing computational thinking education, AI literacy, and technology-enhanced learning. Notably, she was recognized among the world's top 2% scientists by Stanford University from 2020 to 2024. Professor Hsu has served as the editor of Taiwan's official Information Technology textbooks for secondary education. She currently serves as the principal investigator of Taiwan’s Ministry of Education Micro-Credential Program in Educational Big Data, leading national efforts to advance data-driven education.

Title: Taiwan’s Educational Big Data Microprogram (2022–2025): Leveraging Data Evidence and Talent Development to Enhance K–12 Learning

Abstract: This presentation introduces Taiwan’s Educational Big Data Microprogram (2022–2025), a three-phase national initiative to develop talent and promote data-informed education. Universities created microprograms based on their institutional strengths, offering courses and hands-on projects in educational data analytics. Students collaborated with K–12 digital learning platform providers and 22 local governments to solve real-world problems, such as analyzing student learning behaviors and evaluating educational outcomes. The program strengthened students’ data literacy and fostered meaningful connections between higher education and K–12 data innovation.

Panelist 4. Prof. Yanjie SONG, Education University of Hong Kong, Hong Kong

Bio: Professor Yanjie Song is Professor at Department of Mathematics and Information Technology at The Education University of Hong Kong. She obtained her PhD in Educational Technology at The University of Hong Kong, and her MEd at the University of Leeds, UK. Her research focuses on AI and the metaverse in education, and multimodal learning analytics (MMLA). She leads her team in developing the metaverse platforms Learningverse and LearningverseVR, designed to support immersive interactive and collaborative learning leveraged by generative AI. Her research employs an MMLA approach to investigate learners’ experiences in these environments. Learn more at her profile here.

Title: Unlocking Adaptive Support for Self-Regulated Learning with GenAI Agents in Immersive VR

Abstract: How do learners regulate themselves in real time when supported by GenAI agents in immersive virtual environments? In this sharing, I will present the findings from a quasi-experimental study comparing college students’ SRL behaviours during oral tasks in immersive VR, guided either by scripted or GenAI agents. Using process mining and behavioural analytics, the research revealed that GenAI support prompted richer, more reflective SRL strategies.

Panelist 5. Prof. Hiroaki Ogata, Kyoto University, Japan

Bio: Professor Ogata serves at both the Academic Center for Computing and Media Studies and the Graduate School of Informatics. His research focuses on areas such as computer-supported ubiquitous and mobile learning, learning analytics, educational data science, and personalized learning environments. With over 14,000 citations, h-index of 55, and i10-index 267, Professor Ogata is a highly influential scholar.

Moderator. Prof. Chengjiu YIN, Kyushu University, Japan 

Bio: Professor Yin is a Professor at Research Institute For Information Technology, Kyushu University, Japan. He was a Visiting Scholar at the Department of Computer Science & Engineering of the University of Minnesota, United States in 2018. He is a member of IEEE, IPSJ, JSET, JSiSE and APSCE. His research interests include learning analytics, educational data mining, context-aware ubiquitous learning, mobile learning and language learning. He won Early Career Research Award 2019 in APSCE (Asia-Pacific Society for Computers in Education).