Year: 2026
Type: conference-paper
Abstract: Temporal dynamics in learning behavior can be revealed through period segmentation in Transition Network Analysis (TNA). Cristea et al. demonstrated that segmenting courses into halves and quarters reveals how learning strategies evolve and relate to academic performance. Building on this approach, we investigate whether Topological Data Analysis (TDA), specifically connected components ( $$\beta _0$$ ) change points from Zigzag Persistent Homology, can provide data-driven period boundaries that identify intervention windows. Analyzing 22 courses from the Open University Learning Analytics Dataset, we find that $$\beta _0$$ -based segmentation captures greater between-period variation than time-based segmentation (median variance ratio (VR) = 4.10 $$\times $$ ; 21/22 courses show VR > 1.1). Permutation tests confirmed significance ( $$p < 0.05$$ ) in 18% of individual courses, with 73% showing positive improvement over random breakpoints. Only one course showed better performance with time-based segmentation. However, analysis of academic outcomes reveals a key insight: final-period behavior shows lower correlation with outcomes in $$\beta _0$$ -based segmentation than in time-based segmentation, reflecting a marked behavioral collapse where engaged learners rapidly disengage. We interpret this as evidence that final-period behavior reflects rather than causes outcomes: students who will pass maintain engagement, while those who will fail disengage. This reframes the value of $$\beta _0$$ : rather than improving prediction, change points identify intervention windows. These are periods where behavioral structure shifts and targeted support may be most effective.
Authors: Hitoshi Inoue, Koichi Yasutake
Institutions: Nakamura Gakuen University, Hiroshima University
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
Awards: Theoretical foundations of cooperative learning as dynamic processes ofnetwork dynamics, Empirical Studies on Learning Community Analysis Applying Network Dynamics Theory, Advancing Learning Analytics via the Fusion of Temporal Networks Analysis and Topological Data Analysis, Pioneering New Learning Analytics for Diverse Educational Data
OpenAlex ID: W7201844834
