Interpreting Deep Knowledge Tracing Model on EdNet Dataset

TL;DR

This paper explores the interpretability of deep knowledge tracing models using the large EdNet dataset, demonstrating preliminary effectiveness of interpretation methods and highlighting the need for further research.

Contribution

It extends previous interpretability studies of knowledge tracing models to a larger, more comprehensive dataset, EdNet, and evaluates the effectiveness of interpretation techniques.

Findings

Interpretation techniques are effective on EdNet dataset

Preliminary results show promise for model interpretability

Further research is needed for comprehensive understanding

Abstract

With more deep learning techniques being introduced into the knowledge tracing domain, the interpretability issue of the knowledge tracing models has aroused researchers' attention. Our previous study(Lu et al. 2020) on building and interpreting the KT model mainly adopts the ASSISTment dataset(Feng, Heffernan, and Koedinger 2009),, whose size is relatively small. In this work, we perform the similar tasks but on a large and newly available dataset, called EdNet(Choi et al. 2020). The preliminary experiment results show the effectiveness of the interpreting techniques, while more questions and tasks are worthy to be further explored and accomplished.