Discovering prerequisite relationships between knowledge components from an interpretable learner model

Olivier Allègre (1) , Amel Yessad (1) , Vanda Luengo (1)

1 MOCAH - Modèles et Outils en ingénierie des Connaissances pour l'Apprentissage Humain

We propose in this work a novel approach to retrieve the prerequisite structure of a domain model from learner traces. We introduce the E-PRISM framework that includes the causal effect of prerequisite relationships in the learner model for predicting the learner’s performance with knowledge tracing. By studying the distribution of the learned values of each learner model parameter from synthetic data, we propose new metrics for measuring the existence, direction, and strength of a prerequisite relationship. We apply the same methodology to real-world datasets and observe promising results in retrieving the prerequisite structure of a domain model from learner traces.

Mots clés: Learner modeling; prerequisite structure; data mining; Bayesian networks; knowledge tracing

Domaines: Environnements Informatiques pour l'Apprentissage Humain; Informatique [cs]

Olivier Allègre, Amel Yessad, Vanda Luengo. Discovering prerequisite relationships between knowledge components from an interpretable learner model. 16th International Conference on Educational Data Mining, The Indian Institute of Science Campus, Jul 2023, Bengaluru, India. pp.490-496, ⟨10.5281/zenodo.8115738⟩. ⟨hal-04161385⟩