Maps Show How Twitter Can Be Used To Predict Heart Disease Better Than Regular Methods

Twitter isn't just for sharing cat photos. The service can also be used to map rates of heart disease, researchers from the University of Pennsylvania have found.

The study, published in Psychological Science on Jan. 20, finds that emotions such as anger, stress, and fatigue are expressed through tweets and are associated with higher heart disease risk. In reverse, positive emotions like excitement point towards a lower chance of illness.

Known risk factors for heart disease, like chronic stress, are expensive and hard to map on a large scale, the study's authors explain. But Twitter provides a useful "window into a community's collective mental state" because people sharing their candid feelings and thoughts in a constant stream. Twitter is the ideal platform to look at a large number of people since it's such a huge jumble of voices.

"With billions of users writing daily about their daily experiences, thoughts and feelings, the world of social media represents a new frontier for psychological research," the researchers said. "Such data could be an invaluable public health tool if able to be tied to real-world outcomes."

Focusing on the US, the researchers used public tweets sent between 2009 and 2010. Only people who made their locations known were studied. The researchers then compared the language of tweets from 1,300 counties with health data from the Centers for Disease Control and Prevention.

From the graphic below, you can see that the map of heart disease rates predicted by Twitter (right) is strikingly similar to the one that shows actual recorded death rates from heart disease.

In fact, researchers said that Twitter can get a better pictures of heart disease rates than traditional methods.< A model based only on Twitter language predicted "mortality significantly better than did a model that combined 10 common demographic, socioeconomic, and health risk factors, including smoking, diabetes, hypertension, and obesity," the study said.

Here's a key takeaway:

Negative emotional language and topics, such as words like "hate" or expletives, remained strongly correlated with heart disease mortality, even after variables like income and education were taken into account. Positive emotional language showed the opposite correlation, suggesting that optimism and positive experiences, words like "wonderful" or "friends," may be protective against heart disease.

The relationship between language and mortality is particularly surprising, since the people tweeting angry words and topics are in general not the ones dying of heart disease. But that means if many of your neighbours are angry, you are more likely to die of heart disease.

>The university notes that the correlation between language and emotional states has long been studied to understand physical outcomes, so Twitter was an "ideal candidate" to analyse the indicators of coronary heart disease.