K-means clustering of LMS log data identified two distinct SRL profiles (high and low) among online students¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person
Design limits · Mutluhan Yilmaz 2026: no comparison group (read from the study by two models, 2026-10-29)

Subclaims¶

q3 i? Clustering pre-intervention trace data yielded a reliable two-cluster solution with 52 high-SRL and 42 low-SRL students. → Mutluhan Yilmaz 2026

Evidence¶

Mutluhan Yilmaz 2026¶

Mutluhan Yilmaz, Andrea Gauthier, Mutlu Cukurova. (2026). Supporting online learners' regulation skills with the help of learning analytics and generative artificial intelligence. Education Tech Research Dev. https://doi.org/10.1007/s11423-026-10595-1

q3 · i? · causal · r2

K-means clustering on Phase 0 LMS trace data from 94 students, using the Ye and Pennisi (2022) framework proxies; "The silhouette coefficient score (SC = 0.5774) indicated that the data fit well into two clusters", with 52 high and 42 low SRL participants.

"The silhouette coefficient score (SC = 0.5774) indicated that the data fit well into two clusters. According to Kaufman and Rousseeuw (2009), a silhouette score of 0.5 or above suggests a reliable clustering solution."

Discussion¶

Related Claims¶

• Exploratory K-means clustering identifies four heterogeneous student AI-user profiles differing in experience, competence, usefulness, trust, and control, but the solution's optimality and stability are not established — related
• K-means clustering of K–8 students' platform trace data yields seven distinct engagement profiles — related
• Four distinct action-control belief profiles (agentic, moderate, avoidant, and mixed) emerge among Finnish ninth graders — related
• Three distinct learner profiles emerge from function art activities: Repetitivists, Simplists, and Multifunctionists — related
• Clustering of association rules yields four distinct strategy-combination profiles characterizing lower digital distraction — related
• Latent profile analysis of pre-service teachers' CT skills identifies three profiles (Novice, Developing, Proficient), revealing heterogeneous, non-linear skill acquisition — related
• Teachers' post-workshop platform engagement fell into three behavioral profiles, with most teachers showing minimal creation and browsing — related
• Four distinct LLM learner profiles emerge from latent class analysis of learning contexts, tasks, and devices — related
• The three LMS-derived engagement states (Active, Average, Disengaged) differed significantly on all eight LMS activity indicators — related