Communications of the ACM
How Twitter Knows You're Obese
An Illinois Institute of Technology professor has found that tweets can accurately predict a county's rates of obesity, diabetes, teen birthds, health insurance coverage, and access to health foods.
Credit: Joe Tan/Reuters
Research by Illinois Institute of Technology professor Aron Culotta has found that tweets can accurately predict a county's rates of obesity, diabetes, teen births, health insurance coverage, and access to health foods. As a result, Culotta says Twitter and other social media can complement other data sources for public health officials to identify at-risk communities and offer support.
For each of the 100 most populous counties in the United States, he collected 27 health-related statistics, as well as more than 1.4 million user profiles and 4.3 million tweets over a nine-month period. Culotta then conducted statistical analyses to identify how accurately the health outcomes can be predicted from the Twitter data and which linguistic markers are most predictive of each statistic. He found models that augmented demographic variables, such as race, age, gender and income, with linguistic variables from Twitter that were more accurate than models using demographic variables alone.
"Twitter activity provides a more fine-grained representation of a community's health than demographics alone," Culotta says. "The reason for this appears to come from the insights Twitter provides into personality, attitudes, and behavior, which in turn correlate with health outcomes."
He will present his research at the ACM CHI Conference on Human Factors in Computing Systems, April 26-May 1, in Toronto.
From Illinois Institute of Technology
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found