Detecting Depressed Users in Online Forums

Abstract

Depression is the most common mental illness in the U.S., with 6.7% of all adults who have experienced a major depressive episode. Unfortunately, depression extends to teens and young users as well, and researchers observed an increasing rate in the recent years (from 8.7% in 2005 to 11.3% in 2014 in adolescents and from 8.8% to 9.6% in young adults), especially among girls and women. People themselves are a barrier to fight this disease as they tend to hide their symptoms and do not receive treatments. However, protected by anonymity, they share their sentiments on the Web, looking for help. In this paper, we address the problem of detecting depressed users in online forums. We analyze user behavior in the Rea-chOut.com online forum, a platform providing a supportive environment for young people to discuss their everyday issues, including depression. We examine the linguistic style of user posts in combination with network-based features modeling how users connect in the forum. Our results show that network features are strong predictors of depressed users and, by combining them with user post linguistic features, we can achieve an average precision of 0.78 (vs. 0.47 of a random classifier and 0.71 of linguistic features only) and perform better than related work (F1-measure of 0.63 vs. 0.50).