Knowledge Graph Enhanced Intelligent Tutoring System Based on Exercise Representativeness and Informativeness

This paper proposes KG-EIR, a knowledge graph-enhanced intelligent tutoring system that recommends exercises based on exercise representativeness and informativeness, using a novel Neural Attentive Cognitive Diagnosis model to predict student performance and estimate knowledge states. The framework combines multi-dimensional knowledge graphs with exercise features to select high-quality exercises and was evaluated on two educational datasets showing improved student performance.

In the realm of online tutoring intelligent systems, e-learners are exposed to a substantial volume of learning content. The extraction and organization of exercises and skills hold significant importance in establishing clear learning objectives and providing appropriate exercise recommendations. Presently, knowledge graph-based recommendation algorithms have garnered considerable attention among researchers. However, these algorithms solely consider knowledge graphs with single relationships a

Study Type

Source

Framework Categories

Tool Types

Tags