An Overview on Automatic Detection of Mental Disorders and Risky Behaviours in Social Media

The intense use of social media as communication space among young people has leveraged the prevalence of certain mental disorders and risky behaviours, like cyberbullying, depression, eating disorders, gambling or suicidal ideation. For years, the scientific community has researched in monitoring approaches for the detection of such problems, in order to activate prevention or mitigation strategies and, in severe cases, clinical treatment. Natural Language Processing is one of the most active disciplines dealing with the automatic detection of mental disorders and risky behaviours in social media. This paper offers a wide, updated and extensive review of methods, features, algorithms, scientific forums and projects focused on the automatic detection of these problems over the most popular social networks. Our compilation provides a good starting point for researchers working on this domain or aiming to tackle it. Additionally, some challenges have been identified for enlightening future research lines.