Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing

This paper presents KCQRL, a framework that uses LLMs to automatically annotate knowledge concepts in math questions and learns semantic embeddings to improve knowledge tracing models, which predict student performance over time in online learning platforms. The framework is evaluated on two large real-world math learning datasets and shows consistent improvements across 15 knowledge tracing models.

Knowledge tracing (KT) is a popular approach for modeling students' learning progress over time, which can enable more personalized and adaptive learning. However, existing KT approaches face two major limitations: (1) they rely heavily on expert-defined knowledge concepts (KCs) in questions, which is time-consuming and prone to errors; and (2) KT methods tend to overlook the semantics of both questions and the given KCs. In this work, we address these challenges and present KCQRL, a framework f

Source

Framework Categories

Tool Types

Tags