Analysis of user-generated content from online social communities to characterize and predict depression degree

The identification of a mental disorder at its early stages is a challenging task because it requires clinical interventions that may not be feasible in many cases. Social media such as online communities and blog posts have shown some promising features to help detect and characterize mental disorder at an early stage. In this work, we make use of user-generated content to identify depression and further characterize its degree of severity. We used the user-generated post contents and its associated mood tag to understand and differentiate the linguistic style and sentiments of the user content. We applied machine learning and statistical analysis methods to discriminate the depressive posts and communities from non-depressive ones. The depression degree of a depressed post is identified by using variations of valence values based on the mood tag. The proposed methodology achieved 90%, 95% and 92% accuracy for the classification of depressive posts, depressive communities and depression degree, respectively.