How to spot a flu outbreak on Twitter
New York’s flu outbreaks are being tracked on Twitter in a bid to show the social network can reliably track medical trends.
Experts have created ‘word clouds’ to scan tweets to find those associated with an infection.
They believe the system could eventually be used to track national trends as flu and other viruses spread.
The team from Johns Hopkins and George Washington universities project is the first to prove the social network can accurately gauge the spread of flu at the local level.
The finding, published in a recent issue of the journal PLoS ONE, could give hospital administrators warning they need to make sure they have enough beds and staff to cope with an increased influx of patients.
An early alert can also lead local health officials to boost efforts to vaccinate healthy residents to help contain the virus, the team said.
Citing data from the 2012-2013 U.S. flu season, the researchers reported on results they obtained by sifting through billions of tweets to identify flu infections-as opposed to people merely talking about the flu-and where these flu patients were located.
‘We found that we could do just as well in predicting flu trends in New York City as we did nationally,’ said Mark Dredze, an assistant research professor of computer science at Johns Hopkins who supervised the research.
‘That’s critical because decisions about what to do during a flu epidemic are largely made at the local level.’
The team used software developed in Dredze’s lab to scan through hundreds of millions of tweets, which are messages or comments-each no more than 140 characters-that are posted on Twitter.
Many Twitter users list the cities where they live or use a GPS-equipped cell phone to tweet.
This information allows the researchers to focus on posts from particular geographic areas.
The team’s software is also designed to distinguish between a tweet from someone who likely is ill with flu, as opposed someone who is merely worried about catching the flu. To isolate New York City area tweets related to flu infections, the researchers looked for Twitter user location names associated with that area.
During last year’s severe flu season, running from Sept. 30, 2012, through May 31, 2013, the team members compared their national Twitter flu findings with data that the U.S. Centers for Disease Control and Prevention had collected from healthcare providers.
For the first time, the researchers isolated flu patient tweets from a smaller geographic area-the five boroughs of New York City and some adjoining communities-and compared their results with flu cases compiled by the New York City Department of Health and Mental Hygiene.
‘Not only did our results track trends on the national level, but they also did so on the local level,’ said Broniatowski.
‘It gives our system validity.
‘It shows that we’re measuring what we say we’re measuring, that we’re tracking very useful information. ‘And that localized data is valuable because the flu activity in, say, Boise, Idaho, may be quite different from the national flu trends.’
Broniatowski suggested that the techniques used to track flu trends via Twitter data might also be applied to the study of subjects such as crime, political developments and response to natural disasters.
Paul, the graduate student on the team, added, “The exciting results we’ve come up with so far bring up new questions that will require additional data that the Twitter grant program may enable us to work with.
© Daily Mail, London