Twitter knows when you're going to have a heart attack

"Twitter seems to capture a lot of the same information that you get from health and demographic indicators," said Gregory Park.

By Brooks Hays

PHILADELPHIA, Jan. 21 (UPI) -- Twitter's fast pace and knack for promoting public spats can surely raise heart rates and get the proverbial blood boiling, but the platform known for hashtags and half-formed thoughts can also predict heart attacks -- or at least rates of heart disease.

According to a new study led by researchers at the University of Pennsylvania, Twitter's data can be used to measure a place's psychological and physiological well-being, thus forecasting a community's heart health.


Of course, any public health expert can get together with a geographer or census researcher and use known figures like obesity rates, age, race, as well as socioeconomic indicators to anticipate health problems.

But the new research shows that by analyzing the emotional tone of tweets, Twitter can do the job nearly as well.

To confirm the efficacy of their new analysis and data-mining techniques, researchers compared their prediction results with heart attack data from the CDC. Photo by University of Pennsylvania.

The study found that communities featuring residents prone to angry tweets tinged with frustration and bitterness were more likely to suffer high rates of coronary heart disease, even after controlling for factors like income and education. In contrast, cities, towns and neighborhoods where people tended to express happiness and elation via their tweets were also more likely to enjoy better heart health.


"Psychological states have long been thought to have an effect on coronary heart disease," Margaret Kern, an assistant professor at the University of Melbourne, Australia, explained in a recent press release.

"For example, hostility and depression have been linked with heart disease at the individual level through biological effects," Kern added. "But negative emotions can also trigger behavioral and social responses; you are also more likely to drink, eat poorly and be isolated from other people which can indirectly lead to heart disease."

The takeaway is that the language of Twitter aggregates information on the human condition (whether health related or otherwise). Finding ways to mine that language for trends and tendencies is potentially more valuable than traditional demographic analysis.

"Twitter seems to capture a lot of the same information that you get from health and demographic indicators," concluded Penn researcher Gregory Park. "But it also adds something extra. So predictions from Twitter can actually be more accurate than using a set of traditional variables."

The new research was published this week in the journal Psychological Science.

Latest Headlines