Difficulty-Based Knowledge Point Clustering Algorithm Using Students’ Multi-Interactive Behaviors in Online Learning

To improve learners’ performance in online learning, a teacher needs to understand the difficulty of knowledge points learners different cognitive encounter levels learning process. This paper proposes difficulty-based point clustering algorithm based on collaborative analysis multi-interactive behaviors. Firstly, combining group-directed path network, forgetting factors and degree student-system interaction, we propose measurement model calculate similarity between interactive behavior. Secondly, solve data sparsity problem an improved student-teacher student-student Finally, matrix is obtained by integrating from behavior, The spectral used achieve classification matrix. experiments real datasets show that proposed method has better results than existing methods.