SocialText: A Framework for Understanding Mental Health from Digital Communication Patterns

Over 35% of the world’s population uses social media. Platforms like Facebook, Twitter, and Instagram have radically impacted the way individuals interact and communicate. These platforms facilitate both public and private communication with strangers and friends alike, providing rich insight into an individual’s personality, health, and wellbeing. In this work, we present a generalized framework that outlines a clear, comprehensive method for creating informative, organized feature spaces, used to analyze the semantics of social media discourse. We then demonstrate the efficacy of our framework by applying it to a sample of private Facebook messages in a college student population (N = 103). Our results reveal key individual differences in temporal and relational behaviors, as well as language usage in relation to validated measures of trait-level anxiety, loneliness, and personality. By leveraging the comprehensive structure outlined by our framework, we not only built more complete models of private social media discourse but also demonstrated the associated affordances with respect to classifying mental health. This work represents a critical step forward in linking features of private social media messages to validated measures of mental health and wellbeing.