Hybrid Explainable Framework for Student Mental Health Prediction

Student mental health is now a major problem due to rising academic pressure and lifestyle issues. When it comes to forecasting mental health issues and academic achievement, artificial intelligence is crucial. Using machine learning, deep learning, natural language processing, and multimodal techniques, this review paper investigates recent research on student mental health evaluation. The performance, accuracy, and practical application of several techniques, including Explainable Artificial Intelligence and Random Forest, are evaluated and contrasted. The study points out significant shortcomings in current systems, such as their lack of real-time monitoring, poor interpretability, and lack of customisation. To address these issues, a hybrid multimodal framework is put forth that combines explainable AI techniques with behavioral, textual, and physiological data to enhance prediction accuracy, transparency, and individualized mental health care.