Predicting Learning Behavior Using Log Data in Blended Teaching

Online and offline blended teaching mode, the future trend of higher education, has recently been widely used in colleges around globe. In article, we conducted a study on students’ learning behavior analysis student performance prediction based data about logs three consecutive years college’s “Java Language Programming” course. Firstly, from diverse platforms such as MOOC, Rain Classroom, PTA, cnBlog are integrated preprocessed. Secondly, novel multiclass classification framework, combining genetic algorithm (GA) error correcting output codes (ECOC) method, is developed to predict grade levels students. GA designed realize both feature selection binary classifier fit ECOC models. Finally, key factors affecting grades identified line with optimal subset features selected by GA, which can be analyzed for significance. The results show that this article effectively compared other algorithms. addition, corresponding behaviors pedagogically instructive.