Using Twitter To Track Down Heart Disease
Why does one community have higher levels of heart disease than another? Some of the reasons are obvious, such as income and education levels or local eating and exercise norms.
But as epidemiologists have long argued, other likely factors are more ephemeral. Among them: how angry or content the residents tend to feel, and whether the environment fosters a sense of social connectedness.
Measuring such things is tough, but newly published research reports telling indicators can be found in bursts of 140 characters or less. Examining data on a county-by-county basis, it finds a strong connection between two seemingly disparate factors: deaths caused by the narrowing and hardening of coronary arteries and the language residents use on their Twitter accounts.
“Given that the typical Twitter user is younger (median age 31) than the typical person at risk for atherosclerotic heart disease, it is not obvious why Twitter language should track heart disease mortality,” writes a research team led by Johannes Eichstaedt and Hansen Andrew Schwartz of the University of Pennsylvania. “The people tweeting are not the people dying. However, the tweets of younger adults may disclose characteristics of their community, reflecting a shared economic, physical, and psychological environment.”
The researchers analyzed 148 million messages tweeted from 1,347 American counties between June 2009 and March 2010. Emotional language was measured in two ways: the use of common terms associated with concepts such as anger, anxiety, and “positive and negative social relationships” and clusters of words reflecting certain attitudes and topics, including hostility and aggression, boredom and fatigue, optimism, and positive experiences.
This information was compared with county-level, age-adjusted mortality rates for atherosclerotic heart disease, as well as such factors as median income, high school and college graduation rates, and the prevalence of known risk factors like diabetes, obesity, and smoking.
The key results: “Greater usage of anger, negative-relationship, negative-emotion, and disengagement words was significantly correlated with greater age-adjusted AHD mortality,” the researchers report.
On the other side of the equation, “Greater use of positive emotion and engagement words was associated with lower AHD mortality,” they write. “Use of engagement words remained significantly protective after controlling for socioeconomic status.”
Similar associations were found for the aforementioned word clusters, with themes of hostility, aggression, hate, and boredom/fatigue associated with higher levels of atherosclerotic heart disease deaths, and references to positive experiences and optimism related to lower levels.
“Engagement (that is, participation in community activities), which has long been considered…