Personalized Self-Directed Learning Recommendation System Based on Social Knowledge in Distributed Web

Abstract

Personalized self-directed learning recommender systems help users manage their learning paths more effectively. This paper proposed a personalized self-directed learning recommendation system based on social knowledge in cloud-supported web databases. The system leverages Long Short-Term Memory (LSTM) neural networks and Graph Attention Networks (GAT) to enhance the accuracy and effectiveness of recommendations. The LSTM neural network is used for modeling the temporal sequences of learning activities, while the Graph Attention Network is employed to extract knowledge from social interactions and relationships among users. By combining these two models, the system can provide precise and personalized recommendations to users. Experimental results demonstrate that this system can improve learning efficiency by delivering appropriate and timely content, thereby enhancing the users learning experience. The use of cloud databases also ensures easy access and high scalability of the system over distributed web.