Characterizing Geographic Variation in Well-Being Using Tweets


  • Hansen Schwartz University of Pennsylvania
  • Johannes Eichstaedt University of Pennsylvania
  • Margaret Kern University of Pennsylvania
  • Lukasz Dziurzynski University of Pennsylvania
  • Richard Lucas Michigan State University
  • Megha Agrawal University of Pennsylvania
  • Gregory Park University of Pennsylvania
  • Shrinidhi Lakshmikanth University of Pennsylvania
  • Sneha Jha University of Pennsylvania
  • Martin Seligman University of Pennsylvania
  • Lyle Ungar University of Pennsylvania



well-being, social media, natural language processing, Twitter


The language used in tweets from 1,300 different US counties was found to be predictive of the subjective well-being of people living in those counties as measured by representative surveys. Topics, sets of co-occurring words derived from the tweets using LDA, improved accuracy in predicting life satisfaction over and above standard demographic and socio-economic controls (age, gender, ethnicity, income, and education). The LDA topics provide a greater behavioural and conceptual resolution into life satisfaction than the broad socio-economic and demographic variables. For example, tied in with the psychological literature, words relating to outdoor activities, spiritual meaning, exercise, and good jobs correlate with increased life satisfaction, while words signifying disengagement like ’bored’ and ’tired’ show a negative association.




How to Cite

Schwartz, H., Eichstaedt, J., Kern, M., Dziurzynski, L., Lucas, R., Agrawal, M., Park, G., Lakshmikanth, S., Jha, S., Seligman, M., & Ungar, L. (2021). Characterizing Geographic Variation in Well-Being Using Tweets. Proceedings of the International AAAI Conference on Web and Social Media, 7(1), 583-591.