In a rapidly evolving landscape of educational research, explainable artificial intelligence (XAI) and interpretable machine learning (IML) are emerging as pivotal tools that enhance transparency, efficiency, and innovation. This book serves as a comprehensive guide to understanding and leveraging these technologies to transform teaching, learning, and research practices. It aims to bridge the gap between complex technological advancements and practical educational applications. It delves into how XAI and IML can be harnessed to analyze vast educational datasets, assess student performance, and design adaptive learning environments, all while ensuring the interpretability and ethical deployment of AI systems. Through a blend of theoretical insights and real-world examples, the book explores topics such as the foundations of XAI, the development of IML algorithms for education, and the ethical implications of data-driven decision-making. A unique feature of this volume is its interdisciplinary approach, combining perspectives from educators, researchers, and data scientists. It emphasizes collaboration and encourages contributors to address emerging trends, challenges, and opportunities in the application of XAI and IML. Case studies from diverse educational contexts provide practical insights and inspire innovative solutions to pressing educational issues. The book serves as a comprehensive and definitive guide for practitioners and researchers dedicated to enhancing educational processes.
Table of Contents:
Preface. PART I: INTRODUCTION. 1. Explaining Explainability in Education Integrating Data Science, Interpretation, and Human Understanding. PART II: CONCEPTUAL AND HUMAN-CENTERED FOUNDATIONS OF EXPLAINABLE AI IN EDUCATION. 2. C-XplainEd: A Conceptual Framework for Trustworthy XAI Educational Applications. 3. The Relation between Fairness and Explainability in Predictive Modeling of Student Performance: A Study on the OULAD. 4. Human-Centered Explainable AI in Education: Opportunities and Challenges of Large Language Models. 5. When the Model Won’t Explain Itself: EPICC as a Framework for Human-Centered Explainability in Educational AI Use. 6. Human-Centred Approaches for Non-Expert Users in Explainable AI. 7. Evaluating Explainability in Educational AI: A Dual-Perspective Framework with Case Application. PART III: APPLIED AND COMPUTATIONAL INNOVATIONS IN EDUCATIONAL XAI. 8. A Framework for Explainable AI in Automated Grading Systems in Engineering Education. 9. Explaining Grit: Leveraging XAI on Sentiment Analysis of Student-Generated Text. 10. From Local Explanations to Collective Explanations: An XAI Approach Using LIME and Clustering in Education. 11. Beyond the Black Box: XAI Techniques to Interpret Complex Machine Learning Models. 12. A Knowledge-based Neural Network to Interpret Mars Habitat Building Assessment in Minecraft.
About the Author :
Myint Swe Khine has master's degrees from the University of Southern California, USA, and the University of Surrey, UK, as well as a Doctor of Education from Curtin University, Australia. He has worked at the National Institute of Education at Nanyang Technological University, Singapore, and was a Professor at Emirates College for Advanced Education in the United Arab Emirates. He currently teaches at the School of Education, Curtin University, Australia. Dr. Khine is also an Editor-in-Chief of the Journal of Science of Learning and Innovations.
He has published over 40 edited volumes. The most recent publication includes Future of Learning with Large Language Models: Applications and Research in Education (CRC Press, 2026).
