K* detectors identify no-PFL-shallow learners with cross-validated A′ of 0.790 and kappa 0.55¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2013 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? A K* multiplicative-interactions model detects students whose problem-solving performance exceeds their preparation-for-future-learning performance, achieving A′ 0.790 and Kappa 0.55 under student-level cross-validation. → Gowda 2013

Evidence¶

Gowda 2013¶

Gowda, S. M., Baker, R. S., Corbett, A. T., & Rossi, L. M. (2013). Towards Automatically Detecting Whether Student Learning is Shallow. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-013-0006-4

q2 · i? · design · r2

Same detector-development procedure applied to no-PFL-shallowness labels (20 of 71 students labeled shallow). No step regression model could be built because no individual feature had cross-validated Kappa over 0 for this construct; K* models succeeded.

"The multiplicative-interactions model achieved a better A ′ and Kappa than the no-interactions model, achieving an A ′ of 0.790, and a Kappa of 0.55. Excellent precision and recall (for shallowness) were also achieved."

Discussion¶

Related Claims¶

• K* models outperform step regression for detecting transfer-shallowness, with no-interactions and interaction models each best on different metrics — related
• K* detectors identify no-transfer-shallow learners at student-level cross-validated A′ of 0.766–0.791 — related
• Shallowness detectors transfer between the transfer-shallow and PFL-shallow constructs with minimal A′ degradation — related