cs.LGOct 12, 2026

Longitudinal Learner Participation Profiling in Online Learning: Heterogeneous Consensus Clustering under Unequal Observation Windows

Authors: David Otoo-Arthur, Terence L. van Zyl

Organizations: University of the Witwatersrand, Johannesburg, South Africa · University of Johannesburg, Johannesburg, South Africa

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Learning management system traces are clustered to identify participation profiles, but unequal observation windows may cause profiles to reflect duration rather than participation alone. Using 16,448 complete learner--course sequences from 4,599 learners across 152 courses at a South African public university, we evaluated eight participation measures. All remained related to observation-window length even when expressed as rates or shares. Course-grouped adjustment reduced these relationships. Five retained measures were evaluated using K-means, Gaussian mixtures, Ward agglomerative clustering and K-medoids, with standardised measures and principal-component summaries. Evidence supported a broad two-profile grouping and a more detailed adjusted four-profile consensus: Gradually declining, Early-concentrated, Cyclical variable and Sustained active. Profile membership accounted for 2.87% of the variation in duration in the primary consensus, versus 38.18% using original measures. Mean assignment support was 0.739; 8.35% of assignments fell below 0.50, with greatest uncertainty in Sustained active. Two week-by-week sequence analyses agreed strongly with each other but only modestly with the four-profile consensus, indicating that the profiles combined multiple aspects of participation rather than distinct sequence patterns. Profiling should therefore assess duration effects, compare clustering methods and participation summaries, and report assignment consistency.

Figures & tables

Profilenn%AWRRRLIRSMALCMESSupport
Gradually declining4,87329.630.2440.0830.5390.5320.3490.736
Early-concentrated5,19131.560.1100.0600.6770.3190.6780.788
Cyclical variable3,59421.850.4550.1640.2491.0870.3040.743
Sustained active2,79016.960.6220.0610.2500.9460.2310.649
Note. AWR = active-week rate; RR = reactivation rate; LIRS = longest inactive-run share; MALC = mean absolute log change; MES = maximum-week event share. Support is the mean proportion of eight clustering results that agreed with the final profile assigned to each record.
Table 1: Characteristics and support of the primary participation profiles
More in this topic

Educational Data Mining

Educational Data Mining studies computational methods for analyzing learning data to understand learners, improve instruction, and support educational decisions.

See all 72 papers

Explore similar work

CardsList
Oct 1, 2026

Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses

Asynchronous online learning offers temporal flexibility at a structural cost: learning communities tend to fragment rather than cohere. β0β_0, the number of disconnected behavioral clusters from Zigzag Persistent Homology, serves as a cohort-level indicator of this structure. Two questions remained unverified at scale: (1) does apparent β0β_0 convergence reflect genuine behavioral alignment or learner dropout? and (2) do assessment deadlines produce reproducible fragmentation-convergence cycles? We address both across all 22 OULAD courses (N > 22,000; 857 week-pairs). Changes in β0β_0 strongly co-vary with active learner changes (pooled r = 0.387; median per-course r_delta = 0.459, 20/22 courses), identifying β0β_0 as a participation-sensitive indicator: β0β_0 and active learner counts co-respond to deadline events rather than one causing the other. Deadlines produced fragmentation in 82.6% of assessments and the full Fragment First, Converge Later (FFCL) cycle in 60.2%. 3-phase analysis confirmed structural fragmentation as the dominant long-term trajectory (90.9% of courses), moderated by curriculum structure. These findings establish β0β_0 as a participation-sensitive structural indicator with direct implications for AI-augmented learning analytics design.

Hitoshi Inoue, Koichi Yasutake

Nakamura Gakuen University, Japan · Hiroshima University, Japan

Educational Data MiningOnline Learning
AskPDF
Aug 17, 2026

Study-Strategy Clusters from EdNet Logs Track Engagement, Not Mastery

Learning analytics often treats unsupervised clusters of intelligent tutoring system (ITS) logs as learner types that should predict learning. We test that assumption on EdNet-KT3. Clustering study-strategy features (resource use, revision, video, problem practice) for 5{,}000 active learners yields a silhouette-selected parent cut (k=5k=5) with 4 contrast poles (reading-focused, video-heavy, revision-heavy, and problem-first) plus a large near-mean residual (∼\sim64.9%). Reclustering that residual adds four finer styles, giving a bootstrap-stable hierarchy of 8 named strategies. We split each learner's timeline by respond count so clusters use only the early half and outcomes only the late half. Early clusters predict later engagement (continuing to practice and finishing late sessions, especially persistence, η2≈0.106η^{2}\approx 0.106; completion η2≈0.021η^{2}\approx 0.021) but not later unassisted accuracy (correctness on late first-attempts without help; padj≈0.093p_{\mathrm{adj}}\approx 0.093). Volume rises with some styles, yet volume-only clustering barely matches strategy labels (ARI=0.064=0.064). A knowledge-tracing model (SAKT) on the seven TOEIC exam sections predicts next correctness only modestly better than a baseline that knows only how hard each section usually is (AUC lift +0.051+0.051; CI [+0.045,+0.058][+0.045,+0.058]), and that mastery signal is nearly independent of behavior styles (ARI=0.007=0.007). Behavioral clustering here describes study styles and engagement, not knowledge gains.

Qingchuan Lyu, Yingxin Li, Albert Yang

Georgia Institute of Technology, Atlanta, GA, USA · New York University, New York, NY, USA

Educational Data MiningEducationClustering
AskPDF
May 25, 2026

When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Interaction Logs

Early-warning models built from Learning Management System (LMS) logs aim to predict end-of-course outcomes early enough to enable timely learner support. However, reported "early" performance is often inflated by temporal leakage. This occurs when the pipeline uses information that would not yet be available at the time of prediction. We formalize cutoff-based early outcome prediction under a temporal availability constraint and introduce LEAP (Leakage-Excluded Early-Availability Protocol), which enforces cutoff-first truncation prior to joins and aggregation and audits feature provenance to prevent post-cutoff evidence from entering the benchmark. We instantiate LEAP on the public Open University Learning Analytics Dataset (OULAD) as a multi-step protocol for leakage-controlled evaluation across weekly cutoffs. Using several standard learning methods, we evaluate performance using ROC-AUC, PR-AUC, Brier score, and [email protected]. Results show improving performance as the observation window expands, with a marked gain around week~3; Random Forest performs best at the earliest cutoffs, while Gradient Boosting dominates thereafter. Leakage ablations further show that temporal violations, especially through assessment information, can inflate apparent "early" performance.

Ngoc Luyen Le, Marie-Hélène Abel, Bertrand Laforge

Gamaizer, 93340 Le Raincy, France · Université de technologie de Compiègne, CNRS, Heudiasyc (Heuristics and Diagnosis of Complex Systems), CS 60319 - 60203 Compiègne Cedex, France · Sorbonne Université, CNRS UMR 7585, LPMHE (Laboratoire de Physique Nucléaire et des Hautes Énergies), 75252 Paris cedex 05, France

Data LeakageAI in EducationEducational Data MiningTemporal Data LeakageEarly Warning Detection
AskPDF