Depression Identification of Students Based on Campus Social Platform Data and Deep Learning

Abstract

Depression is one of the most common psychological problems faced by human society. Because of less social experience, low psychological endurance, and the multiple responsibilities of future families and society, college students have become one of the most vulnerable groups to suffer from depression. This paper explores an automatic identification method to identify patients with early depression tendency through deep mining of online information of campus social platform users. First, we comprehensively analyze the common characteristics of emotion and behavior on the campus social platform for depression. Secondly, the experimental corpus is formed by preprocessing operations such as deprivation, word segmentation, and denoising of the original data. Finally, the depression recognition is transformed into a text classification problem, and a shallow support vector machine and a deep convolutional neural network model are, respectively, constructed based on the experimental corpus. Combined with the features of depression blog, the algorithm was further improved, and a dual-input convolutional neural network algorithm compatible with multiple features was proposed. The experiments showed that the recognition rate was effectively improved.