Improving Knowledge Tracing Through Learning Processes and Concept Similarity Map

Yingxu Lai, Xinyu Xu, Xiao Zhang, Xinrui Dong, Junxi Zhuang, Jing Liu

Abstract: Knowledge Tracing (KT) aims to track the evolving knowledge states of students based on their historical performance, playing a vital role in online intelligent education systems. While deep learning-based knowledge tracing achieves impressive predictive performance, existing methods suffer from two main shortcomings. Firstly, storing massive amounts of historical information introduces irrelevant noise during the training process. Additionally, individual differences may prevent the model from accurately capturing students comprehensive states. Secondly, deep learning models lack interpretability, failing to provide precise descriptions of students knowledge states. This paper proposes an improved knowledge tracing method through learning processes and concept similarity map (LCKT). We incorporate diverse features, including exercise, exercise difficulty, concept, response time, response, and interval time, to measure the diversity of exercise interactions. Additionally, we utilize a forgetting gate to simulate the decline of students knowledge over time during the learning process. Furthermore, we introduce a concept similarity map as a constraint for model training, which clearly delineates students mastery across different knowledge points. Extensive experiments on three real-world datasets demonstrate that LCKT outperforms state-of-the-art KT methods and exhibits interpretability to some extent.