Topological data analysis reveals key intervention windows in learning behavior
Period Segmentation in Transition Network Analysis: A Topological Data Analysis Approach
Computers and SocietyMachine Learning
Summary
Learning behavior changes over time during a course, but finding exactly when these changes happen can be tricky. The authors used a math tool called topological data analysis to spot moments when student behavior shifts strongly. These change points mark the best times to offer extra help to students, rather than just splitting courses by time periods. They also found that the way students act near the end of a course reflects their likely success rather than predicting it.
What this means in practice
- •For learning platform developers: Detect behavior change points in online courses to time targeted student support interventions effectively.
- •For educational data analysts: Segment course data by topological features to better understand periods of student engagement and disengagement.
Authors
Hitoshi Inoue, Koichi Yasutake
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 ($β_0$) 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 $β_0$-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 $β_0$-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 $β_0$: rather than improving prediction, change points identify intervention windows. These are periods where behavioral structure shifts and targeted support may be most effective.