A Personalized MOOC Learning Group and Course Recommendation Method Based on Graph Neural Network and Social Network Analysis

Massive Open Online Courses (MOOCs) provide extensive educational resources yet often face challenges in sustaining student engagement and motivation. This study aims to mitigate these issues by developing a personalized recommendation system designed to enhance student initiative and overall learning experiences on MOOC platforms. Leveraging data from nearly 40,000 users, this research employs Social Network Analysis (SNA) to investigate the correlation between students' course selection preferences and their academic interest levels, thereby identifying opportunities for tailored educational support. A multi-level network model was constructed using SNA, and an AI-powered assistant utilizing Graph Neural Networks (GNN) was developed to deliver personalized course and study group recommendations; the results demonstrated a significant positive relationship between course preferences and learning engagement, with the GNN-based system effectively enhancing student initiative. This study highlights the significant potential of integrating SNA and GNN for creating data-driven, AI-assisted personalized learning environments in MOOCs, ultimately improving student engagement and educational outcomes.