University of Bristol researchers have released a paper about the utility of Twitter for tracking flu outbreaks, building on research that resulted in Google.org’s Flu Trends.

The researchers gathered a database of more than 50 million geo-located tweets which could then be compared to official data from the U.K.’s national health service on flu incidence by region. By figuring out which keywords in the database of tweets were associated with elevated levels of flu, they were able to create a predictive model that transformed keyword incidence in future tweets into a prediction of the severity of flu for a given area.

Future improvements might involve information from Facebook and other sources of status updates.