Mental Health

Twitter Posts Helpful in Tracking Flu

By Staff Reporter | Update Date: Jan 23, 2013 10:42 AM EST

Twitter posts can help health officials identify a disease outbreak and develop early warning system, says a new study.

The study was conducted by researchers from Brigham Young University who say that the twitter feeds can keep health officials informed about an outbreak and its spread. The study was based on sample size of 24 million tweets from 10 million unique users. Researchers found that in this sample data, accurate information on location can be gathered for about 15 percent of tweets (from accounts that have GPS data).

"One of the things this paper shows is that the distribution of tweets is about the same as the distribution of the population so we get a good representation of the country. That's another nice validity point especially if you're going to look at things like diseases spreading," said BYU professor Christophe Giraud-Carrier in a press release.

Even with many users giving inaccurate information about their location. Researchers found that at least 15 percent of the twitter users provide information about their location and this data is enough for health officials to monitor the spread of flu and provide an early warning to the people in the surrounding areas.

"The first step is to look for posts about symptoms tied to actual location indicators and start to plot points on a map. You could also look to see if people are talking about actual diagnoses versus self-reported symptoms, such as 'The doctor says I have the flu'," said Scott Burton, a graduate student and lead author of the study.

Previous studies have shown that the data available from twitter can be used to track disease levels following a flu-outbreak. An article published last year also showed the use of social networking sites have been obtain information about disease outbreaks, how efficient these sites are in tracking diseases and the potential drawbacks of using such a system.

The present study was published in the Journal of Medical Internet Research.

© 2023 Counsel & Heal All rights reserved. Do not reproduce without permission.

Join the Conversation

Real Time Analytics