Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook

Yusif Ibrahimov, Tarique Anwar, Tommy Yuan

TL;DR

This survey addresses the problem of detecting mental disorders from online social media data using explainable AI. It synthesizes traditional diagnostic methods, data-driven approaches, and XAI techniques, outlining a taxonomy of feature extraction, representation learning, and explainability methods across text and graph domains. The work highlights datasets, evaluation measures, and open challenges, proposing future directions such as multi-modal data integration, temporal modeling, domain-informed learning, and improved GNN explainability. The study aims to guide researchers, clinicians, and policymakers toward transparent, ethical, and effective deployment of MDD detection systems leveraging social media signals.

Abstract

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.

Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook

TL;DR

This survey addresses the problem of detecting mental disorders from online social media data using explainable AI. It synthesizes traditional diagnostic methods, data-driven approaches, and XAI techniques, outlining a taxonomy of feature extraction, representation learning, and explainability methods across text and graph domains. The work highlights datasets, evaluation measures, and open challenges, proposing future directions such as multi-modal data integration, temporal modeling, domain-informed learning, and improved GNN explainability. The study aims to guide researchers, clinicians, and policymakers toward transparent, ethical, and effective deployment of MDD detection systems leveraging social media signals.

Abstract

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.
Paper Structure (25 sections, 11 equations, 2 figures, 4 tables)

This paper contains 25 sections, 11 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Traditional Diagnostic Methods
  3. Data-driven Methods for Detection
  4. Mental health feature extraction
  5. Machine learning on social data for MDD
  6. Convolution-based representation learning
  7. Sequential representation learning
  8. Attention and contextual representation
  9. Graph representation learning
  10. Importance of domain knowledge
  11. Explainability is what we need
  12. Interpretable models
  13. LIME
  14. SHAP and KernelSHAP
  15. LRP
  16. ...and 10 more sections

Figures (2)

  • Figure 1: Workflow of data-driven methods for MDD
  • Figure 2: Explainable AI pipeline for MDD via social media