Enhancing Knowledge Tracing with Concept Map and Response Disentanglement

TL;DR

This paper introduces CRKT, a novel knowledge tracing model that leverages answer choices and concept maps to better understand student misconceptions and improve prediction accuracy in educational settings.

Contribution

CRKT is the first model to incorporate both answer choice disentanglement and concept map information for enhanced knowledge tracing.

Findings

CRKT outperforms existing models in prediction accuracy.

CRKT provides better interpretability of student responses.

CRKT effectively utilizes unchosen responses for insights.

Abstract

In the rapidly advancing realm of educational technology, it becomes critical to accurately trace and understand student knowledge states. Conventional Knowledge Tracing (KT) models have mainly focused on binary responses (i.e., correct and incorrect answers) to questions. Unfortunately, they largely overlook the essential information in students' actual answer choices, particularly for Multiple Choice Questions (MCQs), which could help reveal each learner's misconceptions or knowledge gaps. To tackle these challenges, we propose the Concept map-driven Response disentanglement method for enhancing Knowledge Tracing (CRKT) model. CRKT benefits KT by directly leveraging answer choices--beyond merely identifying correct or incorrect answers--to distinguish responses with different incorrect choices. We further introduce the novel use of unchosen responses by employing disentangled representations to get insights from options not selected by students. Additionally, CRKT tracks the student's knowledge state at the concept level and encodes the concept map, representing the relationships between them, to better predict unseen concepts. This approach is expected to provide actionable feedback, improving the learning experience. Our comprehensive experiments across multiple datasets demonstrate CRKT's effectiveness, achieving superior performance in prediction accuracy and interpretability over state-of-the-art models.