Exercise Hierarchical Feature Enhanced Knowledge Tracing

TL;DR

This paper introduces a hierarchical feature-enhanced knowledge tracing framework that improves student performance prediction by integrating knowledge distribution, semantic, and difficulty features from exercise texts, demonstrating high effectiveness.

Contribution

It presents a novel hierarchical framework that incorporates multiple exercise features to enhance knowledge tracing accuracy, which is a new approach in the field.

Findings

High performance demonstrated in extensive experiments

Effective integration of semantic and difficulty features

Improved accuracy over baseline models

Abstract

Knowledge tracing is a fundamental task in the computer-aid educational system. In this paper, we propose a hierarchical exercise feature enhanced knowledge tracing framework, which could enhance the ability of knowledge tracing by incorporating knowledge distribution, semantic features, and difficulty features from exercise text. Extensive experiments show the high performance of our framework.