Related Experiment Video
Updated: May 16, 2026
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Mental Health Risk Detection From Social Media Text Data: A Scoping Review of the Machine Learning Research
Yiqing He1, Yinning He1, Darong Liu2
1Department of Psychology, Guangzhou University, Guangzhou, China.
Psych Journal
|May 15, 2026
Summary
Machine learning effectively detects mental health risks from social media text. Current research focuses on proxy indicators for conditions like depression and anxiety, aiding population-level monitoring.
Area of Science:
- Computational psychiatry
- Digital mental health
- Social media analytics
Background:
- Machine learning (ML) is increasingly used for mental health risk detection via social media text.
- Existing research lacks a structured overview due to variations in methodology and evaluation.
Purpose of the Study:
- To map the research landscape of ML-based mental health risk detection using social media text.
- To synthesize prevailing research emphases and methodological practices.
Main Methods:
- Scoping review following PRISMA ScR guidelines.
- Searched PubMed, Web of Science, and IEEE Xplore for peer-reviewed articles (Jan 2021-Jan 2026).
- Included studies using ML/deep learning on social media text for mental health risk detection.
Main Results:
- 136 studies were identified, primarily focusing on depression, anxiety, and suicide/self-harm risks.
- Mental health risks were mostly identified using proxy indicators from user-generated content.
- Diverse ML models (traditional, deep learning, Transformers) were used with varied validation strategies.
Conclusions:
- Current research emphasizes proxy-based risk signals over clinical diagnoses.
- Social media-based ML approaches show potential for population-level monitoring and early risk identification.