DESIGNING AN ADAPTIVE RECOMMENDATION SYSTEM IN EDUCATION BASED ON KNOWLEDGE GRAPHS AND ARTIFICIAL INTELLIGENCE

Abstract

Abstract: Modern educational paradigms are rapidly shifting toward personalization, requiring systems that dynamically adapt to the unique learning paces, knowledge gaps, and backgrounds of individual students. Traditional recommendation systems in education often suffer from data sparsity and a lack of semantic understanding regarding the relationships between different learning concepts. This paper proposes a conceptual framework for an adaptive educational recommendation system that integrates Knowledge Graphs (KGs) with Artificial Intelligence (AI) algorithms. By mapping curriculum structures into a semantic graph and leveraging graph neural networks (GNNs) alongside reinforcement learning, the proposed system provides context-aware, sequential learning path recommendations. The architectural design demonstrates a significant potential to improve student engagement, optimize cognitive load, and bridge knowledge gaps effectively.