The Role of Mobile Education Technology in Promoting Personalized Learning in Higher Education

Abstract

With the continuous development of information technology, mobile education technology has gradually gained widespread application in higher education, driving the realization of personalized learning. Personalized learning aims to provide customized learning content and methods based on students’ individual needs, interests, and learning progress, making it an important trend in modern education. However, the challenge of accurately recommending the most suitable learning resources to students through technological means remains a key research issue. In recent years, researchers have proposed various personalized learning recommendation systems, but most studies have not fully explored the complex correlations and nonlinear features in students’ learning behaviors, resulting in suboptimal recommendation accuracy and adaptability. Graph neural networks (GNNs), as an emerging deep learning method, have demonstrated superior performance in multiple fields due to its powerful capability to model node relationships. Personalized recommendation systems based on GNN can effectively capture interactions among learners and complex learning needs, offering more precise recommendations for learning resources. This paper aims to explore how lightweight GNN techniques can enhance the performance of personalized learning recommendation systems in higher education. Specifically, the paper is divided into two parts: first, it discusses the personalized learning recommendation problem based on lightweight GNNs, analyzing the limitations and challenges of existing research; second, it designs a personalized learning recommendation model based on lightweight GNNs and proposes corresponding optimization strategies. This study aims to provide a new solution for personalized learning in higher education, advancing the application and development of educational technology.