Construction of a Psychological Health Monitoring System Based on Social Text Sentiment Analysis

The traditional mental health management model often relies on students to actively seek help, which has certain limitations. With the development of big data and artificial intelligence technology, sentiment analysis methods based on students' social texts provide new ideas for campus mental health monitoring. This study developed a college student mental health monitoring system based on social text sentiment analysis. The system uses sentiment dictionaries and LSTM, a text classification model based on deep learning, to perform real-time sentiment analysis on texts, pictures, videos and other content posted by students on campus social platforms, thereby identifying abnormal signals such as negative emotions and anxiety. The experimental test results show that the LSTM model is superior to the basic RNN model in key indicators such as sentiment analysis accuracy and response time, and can better meet the requirements of the mental health monitoring system for real-time and accuracy. In summary, this study shows that the social text sentiment analysis technology can effectively improve the monitoring ability of campus mental health management and provide an important basis for early intervention.