Twitter can help identify communities at risk of stress, heart disease: study
26 January 2015 04:39

Twitter can help identify communities at risk of stress, heart disease: study

MELBOURNE. KAZINFORM - Australian researchers have discovered how social media can serve as an indicator of a community's psychological wellbeing and can predict rates of heart disease.

The study, conducted by researchers from the University of Melbourne and University of Pennsylvania in the U.S., showed that Twitter not only predicts heart disease risk as well as many other traditional methods, but it also acts as a psychological barometer.

Repeated instances of the negative emotive words such as "hate" and "bored" in local community tweets correlated with a higher heart disease rate in those communities, even after variables such as income and education were taken into account.

The study, to be published in next month's edition of the leading journal Psychological Science, found positive terms like " wonderful" and "friends" were associated with a lower risk of heart disease.

Hostility and chronic stress are known risk factors for heart disease and, researchers said, using Twitter to identify communities most at risk will significantly lower the current cost of large-scale assessments.

Researchers said their Twitter language prediction system worked significantly better than did a model that combined 10 common factors such as smoking status and rates of obesity.

Lead author Dr. Margaret Kern from the University of Melbourne said social media was "a new frontier for social science research".

"Using Twitter as a window into a community's collective mental state may provide a useful tool in epidemiology and for measuring the effectiveness of public-health interventions," Kern said in a press statement released on Thursday.

Randomly sampled tweets from 1,300 counties in the United States, which comprised 88 percent of the country's population, were analyzed.

Coronary heart disease is the world's leading cause of death and proved an ideal measure of their hypothesis that Twitter was an identifier of at-risk communities.

"We can't predict the number of heart attacks a community will have in a given timeframe, but the language may reveal places to intervene," said Kern.

"The world of social media is a new frontier for social science research." Kazinform refers to