E-Learning Behavior Categories and Influencing Factors of STEM Courses: A Case Study of the Open University Learning Analysis Dataset (OULAD)

With a focus on enhancing national scientific and technological competitiveness cultivating innovative talents, STEM education has achieved remarkable results in developing students’ core quality improving academic achievement. Online courses built for have attracted many learners. However, as the number of learners continues to grow, online faces problems such difficulties ensuring teaching learning poor performance students learning. An in-depth exploration correlations between learners’ E-learning behavior categories outcomes will facilitate teachers’ precise interventions who are online. This study first predicts course through machine deep algorithms, then uses factor analysis methods discover behavioral features, random forest algorithm explore vital features that influence courses, finally performs category classification important characteristic behaviors based basis. The show classifications preparation behavior, knowledge acquisition consolidation affect courses. Moreover, series strongly performance. In general, teachers can systematically intervene time at-risk from perspective further improve construction