An Explainable AI-Driven Machine Learning Approach for Student Depression Detection

Student mental health has emerged as a major global concern, with depression being a common problem that has a considerable influence on academic performance and personal well-being. This paper presents an Explainable AI (XAI) enabled machine learning framework for effectively diagnosing depression in students. The model uses advanced machine learning algorithms to examine the dataset which includes behavioral, academic, and demographic aspects, with an impressive accuracy of 98.41%. To provide interpretability and transparency, the framework incorporates XAI techniques like LIME (Local Interpretable Model-agnostic Explanations) and ELI5 (Explain Like I’m 5) to uncover crucial elements that influence predictions. The findings show that specific behavioral patterns and academic indicators are critical in identifying depressed tendencies and providing actionable information for educators and mental health providers. This method promotes trust, accountability, and successful intervention techniques by striking a balance between explainability and predictive performance, with the ultimate goal of improving student’s mental health outcomes.