Psychol Sci. 2015 Jan 20. pii: 0956797614557867. [Epub ahead of print]

Psychological Language on Twitter Predicts County-Level Heart Disease Mortality.

Eichstaedt JC1, Schwartz HA2, Kern ML3, Park G4, Labarthe DR5, Merchant RM6, Jha S7, Agrawal M7, Dziurzynski LA4, Sap M4, Weeg C4, Larson EE4, Ungar LH2, Seligman ME4.

Author information

• 1Department of Psychology, University of Pennsylvania johannes.penn@gmail.com jeich@sas.upenn.edu andy.schwartz@gmail.com.
• 2Department of Psychology, University of Pennsylvania Department of Computer and Information Science, University of Pennsylvania.
• 3Department of Psychology, University of Pennsylvania Graduate School of Education, University of Melbourne.
• 4Department of Psychology, University of Pennsylvania.
• 5School of Medicine, Northwestern University.
• 6Department of Emergency Medicine, University of Pennsylvania.
• 7Department of Computer and Information Science, University of Pennsylvania.

Abstract

Hostility and chronic stress are known risk factors for heart disease, but they are costly to assess on a large scale. We used language expressed on Twitter to characterize community-level psychological correlates of age-adjusted mortality from atherosclerotic heart disease (AHD). Language patterns reflecting negative social relationships, disengagement, and negative emotions-especially anger-emerged as risk factors; positive emotions and psychological engagement emerged as protective factors. Most correlations remained significant after controlling for income and education. A cross-sectional regression model based only on Twitter language predicted AHD mortality significantly better than did a model that combined 10 common demographic, socioeconomic, and health risk factors, including smoking, diabetes, hypertension, and obesity. Capturing community psychological characteristics through social media is feasible, and these characteristics are strong markers of cardiovascular mortality at the community level.