Angry Tweets Help Twitter Detect Heart Disease Risk

New research shows that Twitter can detect not just viruses, but long-term public health problems

Smashed Laptop
Jason Stang/Corbis

Scientists have proven, more than once, that Twitter can predict the spread of a disease like the flu. But recent research shows that tweets—especially angry ones—can measure other public health risks, too: by getting a read on a community’s psychological well-being, they can predict long-term health problems like heart disease.

In a new study, scientists from the University of Pennsylvania and an international team tried to connect prevailing theories about language and emotional states with community health outcomes. They matched tweets with public health data on heart disease and created “emotional dictionaries” to search for tweets that reflected individual psychological states. And even after correcting for variables such as socioeconomic status and education, they learned that tweets that convey negative emotions are closely connected to a community’s heart disease mortality rate.

The message, in fewer than 140 characters? Words matter. Even though individuals who used angry words like “hate” in their tweets didn’t necessarily die of heart disease, others in their community did. And it worked the other way, too—people who tweeted about happiness and optimism seemed to have communities with a lower heart disease risk.

“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,” said H. Andrew Schwartz, a professor of computer and information science who worked on the study. “But that means if many of your neighbors are angry, you are more likely to die of heart disease.”

So does that mean that social media isn’t bad for your health? If it can identify at-risk areas and point public health professional to early intervention, on net, maybe not.

Get the latest stories in your inbox every weekday.