U.S. researchers tracking flu through Twitter

NEW YORK (Reuters) - Researchers and computer scientists at Johns Hopkins University have devised a way to track cases of influenza across the United States using the microblogging site Twitter.

Twitter is full of tweets about the flu, which has been severe and reached epidemic proportions this year, but it has been difficult to separate tweets about the flu from actual cases.

"We wanted to separate hype about the flu from messages from people who truly become ill," said Mark Dredze, an assistant research professor in Johns Hopkins' department of computer science, who monitors public health trends by looking at tweets.

To solve the problem, Dredze and his colleagues developed a screening method based on human language-processing technologies that only delivers real-time information on actual flu cases and filters out the rest of the chatter on the public tweets in the United States.

The researchers at the Baltimore university tested the system by comparing their results with data from the U.S. Centers for Disease Control and Prevention.

"In late December," Dredze said on Thursday, "the news media picked up on the flu epidemic, causing a somewhat spurious rise in the rate produced by our Twitter system. But our new algorithm handles this effect much better than other systems, ignoring the spurious spike in tweets."

The scientists, whose research was funded partly by the National Institutes of Health's Models of Infectious Disease Agent Study, have also produced maps of the United States that show the impact of the flu on each state.

Dredze said he hoped the system could be used to track the other illnesses.

(Reporting by Patricia Reaney,; Editing by Jill Serjeant and Peter Cooney)