Spread of Flu Tracked Via Twitter Activity

1-27-2013 2-27-10 PM

Researchers at Johns Hopkins University have created algorithms that will pore through and analyze everyday tweets to extract public health data on the spread of flu virus.

Validated by comparing results with data from the US CDC, the researchers are excited to have developed a system that can monitor the spread of disease geographically and filter out regional or national spikes caused by local or national media coverage of the flu.

"In late December, 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." – Mark Dredze, assistant research professor at John Hopkins University.

The goal of the project was to separate the hype about flu from messages composed by people who were actually sick. The result is an accurate and stable system that is capable of producing reliable maps of the US that show the impact of the flu on each state.

↑ Back to top

Founding Sponsors

Platinum Sponsors