Analysis of Online Learning Behavior Based on Multi-dimensional Features

At present, the study of personalized student models in large-scale open learning environments often selects the characteristic dimensions of students based on human experience, and there is a lack of research on whether student characteristics are effective to learning behavior analysis or whether it can affect learning effects. It is necessary to explore the impact of learning behavior characteristics on learning effects through data mining, extracting multi-dimensional features that can comprehensively and accurately reflect students’ abilities and preferences, to build a student model suitable for personalized strategy recommendations and resource recommendations. The paper uses log data of online learning platforms to explore the impact of different behavioral dimensions on students’ learning enthusiasm using correlation analysis, independent sample testing and other methods. By discovering the characteristics of different types of students, combining evaluation indicators and improved clustering algorithms, characteristics of 4 groups with different learning strategies are creatively proposed.