Student Behavior Prediction of Mental Health Based on Two-Stream Informer Network

Abstract

Students’ mental health has always been the focus of social attention, and mental health prediction can be regarded as a time-series classification task. In this paper, an informer network based on a two-stream structure (TSIN) is proposed to calculate the interdependence between students’ behaviors and the trend of time cycle, and the intermediate features are integrated layer by layer to realize the prediction of mental health by a gating mechanism. Through experiments on a real campus environment dataset (STU) and an open dataset (MTS), it is verified that the proposed algorithm can obtain higher accuracy than existing methods.