Predicting mental health using social media: A roadmap for future development

TL;DR

This paper reviews machine learning approaches for detecting mental health issues from social media data, providing a roadmap for future research and development in automated mental health screening.

Contribution

It offers a comprehensive overview of current methods, organizing them into data collection, feature extraction, and prediction, and discusses future directions for auto-detection frameworks.

Findings

Machine learning can identify mental health symptoms from social media content.

Recent studies explore various features and analytical methods for disorder prediction.

Auto-detection frameworks can aid large-scale mental health screening and intervention.

Abstract

Mental disorders such as depression and suicidal ideation are hazardous, affecting more than 300 million people over the world. However, on social media, mental disorder symptoms can be observed, and automated approaches are increasingly capable of detecting them. The considerable number of social media users and the tremendous quantity of user-generated data on social platforms provide a unique opportunity for researchers to distinguish patterns that correlate with mental status. This research offers a roadmap for analysis, where mental state detection can be based on machine learning techniques. We describe the common approaches for predicting and identifying the disorder using user-generated content. This research is organized according to the data collection, feature extraction, and prediction algorithms. Furthermore, we review several recent studies conducted to explore different features of candidate profiles and their analytical methods. Following, we debate various aspects of the development of experimental auto-detection frameworks for identifying users who suffer from disorders, and we conclude with a discussion of future trends. The introduced methods can help complement screening procedures, identify at-risk people through social media monitoring on a large scale, and make disorders easier to treat in the future.