On Thursday, a team of computer scientists and researchers at Johns Hopkins University announced that they have developed a new algorithm to better track U.S. influenza cases using Twitter, Reuters reports.
The algorithm uses human language-processing technologies to pinpoint individual flu cases on Twitter while screening out flu-related tweets that do not represent actual cases.
Mark Dredze -- an assistant research professor of computer science at JHU -- said that last month, media hype spurred an uptick in flu-related tweets. "But our new algorithm handles this effect much better than other systems, ignoring the spurious spike in tweets," he said.
The algorithm also allows the team to map flu prevalence in each state.
To test the algorithm, the scientists compared their results with CDC data on the flu (Reaney, Reuters, 1/24). They found that in November and December 2012, their algorithm "demonstrated a substantial improvement in tracking with CDC figures as compared to previous Twitter-based tracking methods," according to the JHU announcement (JHU release, 1/24).
Dredze added that he hopes the algorithm could be used to track other illnesses.
The research was funded in part by NIH's Models of Infectious Disease Agent Study (Reuters, 1/24).