Knowledge Graph-Driven Education Framework: A Case Study of Introduction to Computer Science Course

In the era of big data and Artificial Intelligence (AI), effectively organizing and utilizing massive structured knowledge in computer science education has become a critical challenge. As a potential solution, the knowledge graph, structured around entities and their relationships, enables efficient organization and reasoning over large scale information. To enhance learning outcomes in computer science education, a Knowledge Graph-Driven Learning (KGDL) framework is proposed, which integrates the knowledge graph into instructional design. The proposed framework integrates a dynamic curriculum knowledge graph, graph neural network-based navigation for a personalized learning path, and an intelligent tutoring module that provides adaptive feedback aligned with cognitive principles. The effectiveness of the KGDL framework is validated through case studies involving students in an Introduction to Computer Science course, demonstrating its potential to foster adaptive learning and improve student engagement.