APGKT: Exploiting Associative Path on Skills Graph for Knowledge Tracing

TL;DR

This paper introduces APGKT, a knowledge tracing model that leverages associative paths on a skills graph to better understand and predict students' answering behaviors by considering skill modes and their usage order.

Contribution

The paper proposes a novel KT model, APGKT, which incorporates skill modes derived from skills graph substructures and difficulty levels, enhancing prediction accuracy.

Findings

APGKT outperforms existing models on five benchmark datasets.

Incorporating skill modes improves understanding of student cognitive processes.

The model effectively captures higher-order skill interactions.

Abstract

Knowledge tracing (KT) is a fundamental task in educational data mining that mainly focuses on students' dynamic cognitive states of skills. The question-answering process of students can be regarded as a thinking process that considers the following two problems. One problem is which skills are needed to answer the question, and the other is how to use these skills in order. If a student wants to answer a question correctly, the student should not only master the set of skills involved in the question but also think and obtain the associative path on the skills graph. The nodes in the associative path refer to the skills needed and the path shows the order of using them. The associative path is referred to as the skill mode. Thus, obtaining the skill modes is the key to answering questions successfully. However, most existing KT models only focus on a set of skills, without considering the skill modes. We propose a KT model, called APGKT, that exploits skill modes. Specifically, we extract the subgraph topology of the skills involved in the question and combine the difficulty level of the skills to obtain the skill modes via encoding; then, through multi-layer recurrent neural networks, we obtain a student's higher-order cognitive states of skills, which is used to predict the student's future answering performance. Experiments on five benchmark datasets validate the effectiveness of the proposed model.