For activity-defined engagement prediction in DTA logs, the activity-only Baseline remained strongest, and permutation importance was dominated by activity indicators¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? For activity_defined_engagement, the Baseline model was strongest across held-out metrics, and none of the augmented feature sets materially improved it, reflecting overlap between predictors and the outcome definition. → Wang S and Zhao J 2026

Evidence¶

Wang S and Zhao J 2026¶

Wang S and Zhao J (2026) Reflective AI use and student engagement in AI-supported programming: technology acceptance, programming self-efficacy, and behavioral trace evidence. Front. Psychol. 17:1929887. https://doi.org/10.3389/fpsyg.2026.1929887

q2 · i? · associational · r2

Held-out comparison on the DTA dataset for the activity-defined engagement target, constructed as the mean of standardized activity indicators with students at or above the 67th percentile labeled positive. The article reports "Foractivity_defined_engagement, the Baseline model was strongest across the held-out metrics"; repeated cross-validation produced almost identical ROC-AUC values across configurations. The article notes the label is not an independent psychological criterion.

"Foractivity_defined_engagement, the Baseline model was strongest across the held-out metrics, as expected from the overlap between its predictors and the outcomedefinition."

Discussion¶

Related Claims¶

• Recovery-related behavioral features add only a small, unstable held-out Macro-F1 gain for final-success prediction in DTA logs (0.725 to 0.743), with negligible average window-sensitivity differences — related
• Feature-based model predictive power derives from a large and varied set of features rather than a few dominant variables — reports the opposite