ExplainabilityPrivacyEthicscs.LG
Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook
Yusif Ibrahimov, Tarique Anwar, Tommy Yuan
June 10, 2024
arXiv.org
33 citations
Yusif Ibrahimov, Tarique Anwar, Tommy Yuan
Social media data offers significant potential for mental health screening: The paper identifies that large populations actively share personal information on social media platforms, creating substantial datasets that could help detect mental health issues earlier than traditional diagnostic methods alone.
AI models need to be explainable, not just accurate: The survey emphasizes that mental healthcare decisions require transparency and interpretability. Simply having an AI system that correctly identifies mental disorders is insufficient—healthcare providers and patients need to understand why the system reached its conclusions, which is why explainable AI (XAI) is critical in this domain.
Current AI approaches rely heavily on deep learning but face practical challenges: While modern deep learning methods show promise for mental disorder detection, the paper identifies key issues and challenges in experimental design, dataset availability, and evaluation approaches that researchers must address before these tools can be reliably deployed in real healthcare settings.
Ethical considerations are essential but often overlooked: The paper stresses that mental health decisions demand not just technical accuracy but also ethical considerations. This includes concerns about privacy (since social media data is personal), consent, and potential misuse of mental health predictions derived from online activity.
The field needs standardized practices and datasets: The survey highlights the lack of consistent experimental design and available datasets as a barrier to progress, suggesting that establishing common standards and shared resources would help advance responsible development of AI for mental health detection.
Mental health constitutes a complex and pervasive global challenge, affecting millions of lives and often leading to severe consequences. In this paper, we conduct a thorough survey to explore the intersection of data science, artificial intelligence, and mental healthcare, focusing on the recent developments of mental disorder detection through online social media (OSM). A significant portion of the population actively engages in OSM platforms, creating a vast repository of personal data that holds immense potential for mental health analytics. The paper navigates through traditional diagnostic methods, state-of-the-art data- and AI-driven research studies, and the emergence of explainable AI (XAI) models for mental healthcare. We review state-of-the-art machine learning methods, particularly those based on modern deep learning, while emphasising the need for explainability in healthcare AI models. The experimental design section provides insights into prevalent practices, including available datasets and evaluation approaches. We also identify key issues and challenges in the field and propose promising future research directions. As mental health decisions demand transparency, interpretability, and ethical considerations, this paper contributes to the ongoing discourse on advancing XAI in mental healthcare through social media. The comprehensive overview presented here aims to guide researchers, practitioners, and policymakers in developing the area of mental disorder detection.
Accepted for publication in IEEE Transactions on Artificial Intelligence. \c{opyright} 2026 IEEE (To appear)
Citation data from Semantic Scholar