Explainable AI for Mental Disorder Detection on Social Media: A Survey and Outlook

Abstract

Mental health (MH) is a complex global challenge. The widespread use of online social media (OSM) provides a rich source of data for supporting MH analytics. This article presents a comprehensive review of AI- and data-driven approaches for mental disorder detection (MDD) using OSM, with a particular focus on explainable artificial intelligence (XAI). We summarize traditional diagnostic practices and provide an integrated overview of modern deep learning models, emphasizing how their growing complexity increases the need for transparent and trustworthy explanations. We review a wide range of explainability techniques applied in this domain, including interpretable models, post-hoc attribution methods, attention- and graph-based explanations, and emerging LLM-driven approaches, and outline commonly used datasets and evaluation practices. Finally, we identify key challenges such as data limitations, bias, and the need for clinically meaningful explanations, and propose directions for future research. This survey offers a comprehensive foundation for developing explainable, reliable, and ethically informed MDD systems for social media.