A personalized educational resource recommendation method based on graph neural network

The rise of online education platforms has brought about massive educational resources, as well as problems such as information overload and learning disorientation. Personalized recommendation system can recommend appropriate learning resources for learners according to their interests and learning goals, thus improving learning efficiency and learning experience. In recent years, graph neural networks (GNNs) have made significant progress in graph-structured data representation learning, providing new ideas for personalized educational resources recommendation. In this paper, we propose a personalized educational resource recommendation method based on graph neural network. By constructing a learner-resource interaction graph and utilizing a multimodal fusion model combining graph convolutional network (GCN) and graph attention network (GAT), the method in this paper is able to effectively capture the complex relationship between learners and resources and generate high-quality personalized recommendation results.