DIGITAL: Twitter Can Predict Heart Disease - Study
27 January 2015 at 9:34 am
Researchers from the University of Melbourne and the University of Pennsylvania have shown that social media can serve as a dashboard indicator of a community’s psychological well being and can predict rates of heart disease.
A new study, published in the journal Psychological Science, showed that Twitter not only predicts heart disease risk as well as many traditional factors, but it also acts as a psychological barometer.
The researchers found that expressions of negative emotions, such as “hate”, “bored”, and expletives, in local community tweets were associated with higher heart disease risk, even after variables like income and education were taken into account. However, words like “wonderful” and “friends” were associated with lower risk.
Lead author Dr Margaret Kern from the Centre for Positive Psychology, Melbourne Graduate School of Education, and Johannes Eichstaedt from the University of Pennsylvania said that although researchers assume that the psychological well being of communities is important for physical health, it is hard to measure.
“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,” Dr Kern said.
Drawing on a set of public tweets made between 2009 and 2010, the researchers said they used established emotional expressions as well as automatically generated clusters of words reflecting behaviours and attitudes, to analyse a random sample of tweets from individuals who had made their locations available.
They found there were enough tweets and health data from about 1300 US counties, containing 88 percent of the country’s population.
“Coronary heart disease, the leading cause of death worldwide proved an ideal measure,” Dr Kem said.
“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,” Johannes Eichstaedt said.”
The team said its findings show that these tweets are aggregating information about people that can’t be readily accessed in other ways.
“We believe that we are picking up more long-term characteristics of communities,” Dr Eichstaedt said.
“The world of social media is a new frontier for social science research,” Dr Kem said.