Inspecting Vulnerability to Depression From Social Media Affect

Affect describes a person's feelings or emotions in reaction to stimuli, and affective expressions are found to be related to depression in social media. This study examines the longitudinal pattern of affect on a popular Chinese social media platform: Weibo. We collected 1,664 Chinese Weibo users' self-reported CES-D scores via surveys and three years' worth of Weibo posts preceding the surveys. First, we visualize participants' social media affect and find evidence of cognitive vulnerability indicated by affect patterns: Users with high depression symptoms tend to use not only more negative affective words but also more positive affective words long before they develop early depression symptoms. Second, to accurately identify the type of language that is directly predictive of depression symptoms, we observe ruminations from users who experienced specific life events close to the time of survey completion, and find that: increased use of negative affective words on social media posts, together with the presence of specific stressful life events, increases a person's risk of developing high depression symptoms; and meanwhile, though tending to focus on negative attributes, participants also incorporate problem-solving skills in their ruminations. These findings expand our understanding of social media affect and its relationship with individuals' risks of developing depression symptoms.