College Students' Online Behavior Analysis During Epidemic Prevention and Control

During the novel coronavirus pneumonia epidemic prevention and control period, various network applications have increased, resulting in massive network user behavior data in log form. In order to detect the abnormal behavior, K-means clustering algorithm based on Hadoop is used to cluster the user behavior, and the association rules obtained by mining are used to explain the preference of the campus network users on the access. Then, a prototype system of mobile application network behavior analysis is designed and implemented, which supports feature extraction and application network behavior analysis of mobile application network behavior. The results show that the model can effectively improve the efficiency and accuracy of students' online user behavior analysis, and achieve the purpose of accurate prediction.