Advanced Learning Analytics Methods: AI, Precision and Complexity

This is an open access book.

This comprehensive and timely methodological book introduces several novel topics under the overarching sections of advanced learning analytics (LA), artificial intelligence (AI), precision education, and complex systems. These topics are presented using accessible language, beginning with introductory chapters that cover the fundamentals of each section, followed by step-by-step tutorials featuring code and datasets for various methods within each area. Although the title refers to "advanced LA," the book is written for the broader educational research community and is of interest to quantitative researchers from diverse backgrounds. The first section focuses on Explainable AI and machine learning (ML), with an introduction to the methods, their applications, and tutorials. The second section outlines the foundational concepts of LLMs, their potential applications, and related methodologies, with a tutorial on using LLMs in various analytical tasks. The third section focuses on complex systems, which have become integral to many disciplines and have enabled breakthroughs in modeling intractable problems. Here, three chapters cover Transition Network Analysis (TNA), which fills a critical gap in modeling the temporal unfolding of learning processes over time from a complex systems perspective. The final section addresses precision education, with a particular emphasis on person-centered and person-specific (idiographic) methodologies.

Mohammed Saqr is an Associate Professor of Computer Science at the University of Eastern Finland (UEF). He holds a PhD in learning analytics from Stockholm University, Sweden. Before joining UEF, he completed a postdoctoral fellowship at Université Paris Cité, France, and obtained the title of Docent in learning analytics from the University of Oulu, Finland. Mohammed established and currently leads UEF's Learning Analytics (LA) Unit, recognized as Europe's most productive LA laboratory in the past five years, with a well-established global standing in methodological diversity, innovation, and scientific impact. Mohammed has authored more than 200 peer-reviewed methodological and empirical studies spanning LA, AI, big data and network science. His research pushes the boundaries of precision AI, complexity, and AI. Mohammed Saqr's recent work emphasizes precision AI, where he develops precise, explainable AI to model individuals using idiographic methods, create personalized, explainable AI, and derive unique insights for each person. Methodologically, Mohammed has edited and authored three methodological books and co-founded Transition Network Analysis (TNA), a novel framework providing robust analysis for complex systems and social dynamics. Mohammed is listed among Stanford's Top 2% of World Scientists and named Europe's Emerging Scholar in Learning Analytics. His research has received several awards, including Best Thesis from Stockholm University and Best Paper Awards at LAK 2024, ICCE 2020, SITE 2022 and TEEM 2023 and 2024. He maintains a vast network of collaborators from eight Finnish universities and over 250 scholars across 36 countries. His editorial roles include serving on the boards of the British Journal of Educational Technology, Associate Editor for IEEE Transactions on Learning Technologies, Frontiers in Computer Science, and Frontiers in Education and Academic Editor for PLOS One.

Sonsoles López-Pernas is currently a Senior Researcher and a fellow of the Finnish Research Council (Academy of Finland) at the University of Eastern Finland (UEF, Finland). Sonsoles received her PhD in Engineering from Universidad Politécnica de Madrid (UPM, Spain) on game-based learning in engineering education and the title of Docent from UEF in educational data mining. Sonsoles's work is diverse and interdisciplinary and spans computer science, learning analytics, game-based learning, and computing education. She has over 150 peer-reviewed publications published in well-regarded conferences and journals. She extensively published on longitudinal learning analytics methods, complex systems, network analysis, sequence and process mining as well as machine learning and artificial intelligence. Sonsoles's work has received multiple awards recognizing her contributions to learning analytics, educational technology, and open-source software development. Notably, she received the best PhD thesis award at UPM, the best doctoral thesis award from the Royal Academy of Doctors of Spain (2022), the SoLAR Emerging Scholar Award (Europe) in 2025, and the IEEE TCLT Early Career Researcher Award in Learning Technologies in 2024. Her research has earned best paper awards at major international conferences, including LAK 2024 (Kyoto, Japan), TEEM 2024 (Alicante, Spain), and TEEM 2023 (Bragança, Portugal), best reviewer at ICALT, and other award nominations at EC-TEL and ICALT in 2024. Additionally, she serves as an Associate Editor for IEEE Transactions on Education, Frontiers in Education, and PLOS One. She has recently received a four-year Academy Research Fellowship grant from the Research Council of Finland for the project Optimizing Clinical Reasoning in Time-Critical Scenarios: A Data-Driven Multimodal Approach (CRETIC) and is the principal investigator of several other research projects in learning analytics and game-based learning funded by the European Commission.