Combining cognitive, affective, and metacognitive data from digital workbooks predicts middle-school students' learning productivity with accuracy rising from about 60% to 100% as an inquiry unit progresses¶

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? Machine learning models integrating cognitive, affective, and metacognitive data streams predicted students' productivity with accuracy increasing across the five parts of the unit, reaching adequate accuracy (65% F1) by timepoint P3. → Kubsch 2025

Evidence¶

Kubsch 2025¶

Kubsch, M., Strauß, S., Grimm, A., Gombert, S., Drachsler, H., Neumann, K., & Rummel, N. (2025). Self-regulated Learning in the Digitally Enhanced Science Classroom: Toward an Early Warning System. Educational Psychology Review. https://doi.org/10.1007/s10648-025-10011-9

q2 · i? · associational · r2

Hyperparameter search across 220 ML models (four model types, eleven data-source combinations, five timepoints) with tenfold cross-validation on data from 214 students. Integrated CAM combinations outperformed unimodal ones; "the models that used the aggregated cognitive data (Meta & Emo & agg. knowledge) yielded higher accuracies".

"Overall, combining cognitive, affective, and metacognitive data yielded the highest accuracies (Meta & Emo & all knowledge / Meta & Emo & agg. knowledge), with the models that used the aggregated cognitive data (Meta & Emo & agg. knowledge) yielded higher accuracies than those that used all individual cognitive scores"

Discussion¶

Related Claims¶

• Affective and metacognitive data alone predict learning productivity early in the unit, but cognitive data becomes the stronger predictor in later parts — related
• Machine-learning analysis of multimodal classroom indicators can predict student productivity, and prior knowledge becomes relevant later in the regulation process — a broader claim this one bears on