Optimizing Personalized Learning Paths in Mobile Education Platforms Based on Data Mining

Abstract

With the rapid development of information technology, mobile education platforms have become an integral part of the education sector, demonstrating significant potential in optimizing personalized learning paths. Traditional educational models struggle to provide individualized support tailored to each student’s characteristics and learning progress. However, the integration of big data and artificial intelligence (AI) offers new approaches for constructing personalized learning paths. Data mining techniques analyze students’ learning behaviors and academic performance in depth to recommend suitable learning resources and pathways. Nevertheless, existing research methods face several challenges in practical applications, such as the insufficient utilization of multimodal student data and the inability to dynamically adjust learning paths, limiting the effectiveness and scalability of personalized learning optimization. Most current studies rely on single-source data, lacking a comprehensive analysis of students’ multidimensional learning information. Additionally, traditional collaborative filtering methods suffer from data sparsity and cold-start issues. To address these limitations, this study proposes a collaborative filtering model based on graph convolutional networks, combined with a dynamic optimization mechanism. By leveraging multimodal learning data to construct a comprehensive knowledge graph, this approach enhances the precision of personalized recommendations and dynamically adjusts learning paths according to students’ real-time learning status. The proposed method holds significant academic value and practical applicability in advancing personalized education.