Inproceedings,
Predicting Depression via Social Media
(July 2013)
Abstract
Major depression constitutes a serious challenge in personal
and public health. Tens of millions of people each year suf-
fer from depression and only a fraction receives adequate
treatment. We explore the potential to use social media to
detect and diagnose major depressive disorder in individu-
als. We first employ crowdsourcing to compile a set of
Twitter users who report being diagnosed with clinical de-
pression, based on a standard psychometric instrument.
Through their social media postings over a year preceding
the onset of depression, we measure behavioral attributes re-
lating to social engagement, emotion, language and linguis-
tic styles, ego network, and mentions of antidepressant med-
ications. We leverage these behavioral cues, to build a sta-
tistical classifier that provides estimates of the risk of de-
pression, before the reported onset. We find that social me-
dia contains useful signals for characterizing the onset of
depression in individuals, as measured through decrease in
social activity, raised negative affect, highly clustered
egonetworks, heightened relational and medicinal concerns,
and greater expression of religious involvement. We believe
our findings and methods may be useful in developing tools
for identifying the onset of major depression, for use by
healthcare agencies; or on behalf of individuals, enabling
those suffering from depression to be more proactive about
their mental health.
