Exploratory heat maps reveal three student groups, including disengaged-but-successful students more prevalent in the Python courses, showing low content completion can link to both positive and negative outcomes¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Course-level heat maps showed disengaged at-risk students in all courses and disengaged successful students mainly in Beginners Python and Intermediate Python; module-level maps additionally showed engaged high-performers. → Vincent Zhang 2025

Evidence¶

Vincent Zhang 2025¶

Vincent Zhang, Bryn Jeffries, Irena Koprinska. (2025). A Machine Learning Approach for Predicting Student Progress in Online Programming Education. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-025-00510-9

q2 · i? · associational · r2

Exploratory data analysis plotting course-level and module-level heat maps of problem versus content slide completion (Figs. 5-6), comparing Beginners Python against Beginners Blockly, which share the same slides. The article defines three student groups by slide-completion ranges (Table 2).

"We observe that there is a higher density of disengaged but successful students in the top-left of the Beginners Python heat map. This result provides useful context for modelling student progress — a lack of content slide completion can be linked to both positive outcomes (high problem slide completion) and negative outcomes (low problem slide completion)."

Discussion¶

Related Claims¶

• Attendance, behavior, and course performance (the ABC indicators) reliably predict which secondary students are at risk of dropping out — the general claim this finding bears on, with the studies behind it
• Accounting for learning behavior attenuates profile-related exam score differences, eliminating significance in Python — related
• 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
• Latent profile analysis of pre-service teachers' CT skills identifies three profiles (Novice, Developing, Proficient), revealing heterogeneous, non-linear skill acquisition — related
• The evidence base does not yet provide a menu of program options for helping students at risk of dropping out, and program developers need a way to identify approaches while stronger scientific evidence is developed — related