U. of Penn study: Twitter can predict heart disease rates

Twitter is more than just a social media engine; it also can serve as a dashboard indicator of a community’s psychological well-being and can predict rates of heart disease, according to a University of Pennsylvania study published in Psychological Science.

The researchers analyzed public tweets made between 2009 and 2010 and established emotional dictionaries, as well as automatically generated clusters of words reflecting behaviors and attitudes. There were enough tweets and health data from about 1,300 counties, which contain 88 percent of the national population, according to the study.

In addition to factors like a low income level or smoking, stress also contributes to the risk of heart disease. Expressions of negative emotions such as anger, stress and fatigue in a county’s tweets were associated with higher heart disease risk. Conversely, positive emotions like excitement and optimism were associated with lower risk.

“Getting this data through surveys is expensive and time consuming, but, more important, you’re limited by the questions included on the survey,” said Johannes Eichstaedt, a graduate student in the Department of Psychology. “You'll never get the psychological richness that comes with the infinite variables of what language people choose to use.”

With billions of users writing about their daily experiences, thoughts and feelings, social media offers a new frontier for psychological research, according to the university. In the case of this study, these data are available on a county-by-county level in the U.S. “Such data could be an invaluable public health tool if able to be tied to real-world outcomes,” according to a press release.