Role of artificial intelligence in assisting the management of students with emotional disorders

Abstract Background Students with emotional disorders often exhibit significant emotional fluctuations, difficulty regulating behavior, and decreased academic adaptability in school environments. This undoubtedly puts forward higher requirements for the campus mental health service system. In recent years, artificial intelligence has developed rapidly in emotion recognition, behavior monitoring, and risk warning. Multimodal emotion analysis and intelligent screening tools have been attempted for campus psychological services. However, existing research has mostly focused on single function validation, lacking a systematic evaluation of the overall effectiveness of AI in risk screening, intervention matching, and dynamic tracking from the perspective of student management processes. Therefore, the research aims to construct an artificial intelligence assisted student management model to evaluate the comprehensive role and application value of artificial intelligence in risk identification, behavior management, and emotional intervention for students with emotional disorders. Methods The study adopted a quasi experimental design to screen 120 students diagnosed with emotional disorders through professional scales and interviews from middle schools and universities, and randomly divided them into an AI assisted management group and a conventional management group. The AI system integrates facial expression recognition, speech emotion analysis, and learning behavior data monitoring, generates individual risk indices, and pushes graded intervention recommendations and emotion training tasks. The experimental intervention lasted for 8 weeks, and students were evaluated using the Self Rating Depression Scale (SDS), Self Rating Anxiety Scale (SAS), and Positive and Negative Affect Schedule (PANAS) before and after the intervention. And compare the differences in emotional symptoms and emotional improvement between the two groups according to the experimental procedure. Results The experimental results indicate that the AI assisted management group has advantages in multiple emotional indicators. After 8 weeks, the SDS score of the AI assisted management group decreased by 32.8%, while that of the conventional management group was 15.6% (p.01); The SAS score decreased by 29.4%, significantly higher than the control group's 14.1% (p.01). The PANAS results showed that the AI assisted management group had a 23.7% increase in positive emotion scores and a 26.4% decrease in negative emotion scores, both of which were better than the control group (p.05). In addition, system records indicate that the accuracy of emotion fluctuation recognition has reached 91.2%, and the risk warning is advanced by an average of 4.6 days, indicating a high sensitivity in emotion monitoring. The overall data showed that AI had a significant advantage in improving depression and anxiety. Discussion The research verifies the effectiveness of AI assisted systems in managing students with emotional disorders, which can improve risk identification accuracy, accelerate emotional improvement, and strengthen the continuity of school mental health management. It has important value for building an intelligent campus public health system. In the future, the research sample can be further expanded to include data from multiple campuses, and attempts can be made to combine wearable devices with multimodal neural signals to construct a more accurate emotion management model.