The discourse personalization hint-selection model achieves the highest cross-validated accuracy (86.71%) and F1 (84.81%), significantly above all other models¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? A Random Forest hint-selection model using linguistic, performance-based, and dialogue-history features outperforms random, baseline (linguistic-only), and shallow personalization models on 50-fold cross-validation, with statistically significant improvement at a 95% confidence level. → Kochmar 2022

Evidence¶

Kochmar 2022¶

Kochmar, E., Vu, D. D., Belfer, R., Gupta, V., Serban, I. V., & Pineau, J. (2022). Automated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems. International Journal of Artificial Intelligence in Education, 32, 323–349. https://doi.org/10.1007/s40593-021-00267-x

q2 · i? · design · r2

Cross-validation study (k = 50 folds) of Random Forest hint-selection models trained on 450 recorded student–system interactions. The discourse model reached "86.71% ± 3.34% accuracy and 84.81% ± 3.97% F1 score"; the RANDOM model achieved 53.64% ± 3.99% accuracy.

"The best performing model overall uses DISCOURSE PERSONALIZATION and achieves 86.71% ± 3.34% accuracy and 84.81% ± 3.97% F1 score, which are statistically significant improvements at a 95% confidence level over all other models."

Discussion¶

Related Claims¶

• Random forest algorithms yielded the best classification performance in K–8 MMLA studies comparing multiple machine learning models — a broader claim this one bears on
• Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — related