Twitter Tracks Outbreaks Of Disease
A new study from Brigham Young University says such posts on Twitter could be beneficial to health officials seeking a head start on outbreaks.
The study examined 24 million tweets from 10,000,000 unique users. The study revealed that only 15% of tweets contain accurate location information. This information was taken from user profiles and tweets that contain GPS data. blogging 's likely a critical mass for an early-warning system to identify terms such as "fever," "flu" and "coughing" in the state or city.
Professor Christophe Giraud Carrier, BYU said that one of the things that this paper illustrates is that the distributions of tweets are about the same as the distributions of people. This allows us to get an accurate representation of the nation. "That's an additional good reason to be able to prove that it's valid, particularly if you're planning to look at issues like spreading diseases."
Professor Giraud-Carrier (@ChristopheGC) and his computer science students at BYU report their findings in the latest issue of the Journal of Medical Internet Research.
The researchers discovered surprisingly less information than they anticipated from Twitter's feature that allows tweets to be tagged with a specific location. They found that just 2 percent of tweets had the GPS info. This is lower than the survey results from Twitter users.
"There is this disconnect that's well-known between what you think you are doing and what you are actually doing," Giraud-Carrier said.
Location information can usually be found and parsed from profiles of users. Some people make use of the location field to make a joke. "Somewhere in my imagination" or "a cube world in Minecraft." However, the researchers have confirmed that this user-supplied data was accurate 88 percent of the time. In MINECRAFT to the jokes, a large portion of the errors are due to people tweeting while they travel.
The net result is that public health officials can capture state-level info or better than 15 percent of tweets. This is a good sign for the viability and feasibility of a system based on Twitter for monitoring health issues to supplement the confirmed data from hospitals with sentinel surveillance.
Scott Burton, a graduate student who was the principal author of the study said that "the first step is to look up symptoms that are linked to real-world indicators of location" and then plot the points on the map. "You should also see if anyone is discussing real diagnoses or self-reported symptoms like 'The doctor said I'm sick with the flu.'
Two BYU health science professors collaborated on the project with the computer scientists. Professor Josh West claims that Twitter's primary benefit for health professionals is speed.
West said that public health officials could issue a warning to health professionals for those living in a specific region are experiencing similar symptoms via Twitter. It could prove extremely useful under such conditions.
Kesler Tanner, a BYU student, is a coauthor of the study. He wrote the code to obtain the data from Twitter. When MINECRAFT is in April, he'll be headed into graduate school to obtain an Ph.D.
