Toward Trustworthy Adaptive Learning

This book offers an in-depth exploration of explainable learner models, presenting theoretical foundations and practical applications in the context of educational AI. It aims to provide readers with a comprehensive understanding of how these models can enhance adaptive learning systems. Chapters cover a wide range of topics, including the development and optimization of explainable learner models, the integration of these models into adaptive learning systems, and their implications for educational equity. It also discusses the latest advancements in AI explainability techniques, such as pre-hoc and post-hoc explainability, and their application in intelligent tutoring systems. Lastly, the book provides practical examples and case studies to illustrate how explainable learner models can be implemented in real-world educational settings. This book is an essential resource for researchers, educators, and practitioners interested in the intersection of AI and education. It offers valuable insights for those looking to integrate explainable AI into their educational practices, as well as for policymakers focused on promoting equitable and transparent learning environments.

Bo Jiang is an associate professor at East China Normal University, China. His research interests include intelligent tutoring technologies, computational thinking education, and AI education. He holds academic positions as an executive committee member of the Asia-Pacific Society for Computers in Education (APSCE) and a youth committee member of the Chinese Association for Artificial Intelligence.

Table of Contents Preface Authors Contributors Section I. Explainable Learner Models: An Overview 1. Trustworthy AI for Adaptive Learning 2. Explainable Learner Models: Concepts, Classifications, and Datasets 3. Construction and Interpretation of Explainable Models: A Case Study on BKT Section II. Research on Ante-hoc Explainability Learner Models 4. Interpretable Cognitive State Prediction via Temporal Fuzzy Cognitive Map 5. Improving the performance and explainability of knowledge tracing via Markov blanket 6. Knowledge Tracing within Single Programming Practice Using Problem-Solving Process Data Section III. Research on Post-hoc Explainability Learner Models 7. Understanding the relationship between computational thinking and computational participation 8. Understanding students' backtracking behaviour in digital textbooks: a data-driven perspective Section IV. Toward Trustworthy Adaptive Learning 9. Frameworks for Explainable Learner Models 10. Frameworks for Trustworthy AI for Adaptive Learning Index