Detecting depression and mental illness on social media: an integrative review

Highlights

• Mental illness is underdiagnosed but observable in online contexts.

• Characteristic language use patterns associated with depression have been identified and allow for the detection of mental illness with mixed performance.

• Prediction accuracies fall between unaided clinician assessment and screening surveys.

• No studies to date are based on gold-standard clinical diagnoses.

• The findings are still preliminary and the field relatively nascent.

Although rates of diagnosing mental illness have improved over the past few decades, many cases remain undetected. Symptoms associated with mental illness are observable on Twitter, Facebook, and web forums, and automated methods are increasingly able to detect depression and other mental illnesses. In this paper, recent studies that aimed to predict mental illness using social media are reviewed. Mentally ill users have been identified using screening surveys, their public sharing of a diagnosis on Twitter, or by their membership in an online forum, and they were distinguishable from control users by patterns in their language and online activity. Automated detection methods may help to identify depressed or otherwise at-risk individuals through the large-scale passive monitoring of social media, and in the future may complement existing screening procedures.

Introduction

The widespread use of social media may provide opportunities to help reduce undiagnosed mental illness. A growing number of studies examine mental health within social media contexts, linking social media use and behavioral patterns with stress, anxiety, depression, suicidality, and other mental illnesses. The greatest number of studies of this kind focus on depression. Depression continues to be under-diagnosed, with roughly half the cases detected by primary care physicians [1] and only 13–49% receiving minimally adequate treatment [2].

Automated analysis of social media potentially provides methods for early detection. If an automated process could detect elevated depression scores in a user, that individual could be targeted for a more thorough assessment, and provided with further resources, support, and treatment. Studies to date have either examined how the use of social media sites correlates with mental illness in users [3] or attempted to detect mental illness through analysis of the content created by users. This review focuses on the latter: studies aimed at predicting mental illness using social media. We first consider methods used to predict depression, and then consider four approaches that have been used in the literature. We compare the different approaches, provide direction for future studies, and consider ethical issues.