Disease Outbreaks Are Trackable On Twitter

· 2 min read
Disease Outbreaks Are Trackable On Twitter


A new study from Brigham Young University says such posts on Twitter could actually be beneficial to health officials who want an early warning sign of outbreaks.



The study examined 24 million tweets from 10 million unique users. They determined that accurate location information is available for about 15 percent of tweets (gathered from user profiles and tweets that contain GPS information). That's likely a critical number for an early-warning system to monitor terms like "fever," "flu" and "coughing" in the state or city.



Professor Christophe Giraud Carrier, BYU said that one of the things this study illustrates is that the distributions of tweets are about the same as the distributions of people. This lets us get an accurate representation of the country. "That's another good validity point, especially if you want to examine issues like spreading diseases."



Professor Giraud-Carrier (@ChristopheGC) and his computer science students from BYU present their findings in the latest issue of the Journal of Medical Internet Research.



Researchers discovered that Twitter's location-tagging feature which allows tweets to be tagged with a specific location did not provide the information they expected. They found that just 2 percent of tweets included the GPS information. This is much lower than what Twitter users report in surveys.



Giraud-Carrier stated that there is a disconnect between what you think and what you actually do.



Location information can usually be found and extracted from profiles of users. Some people make use of the location field as jokes. "Somewhere in my imagination" or "a cube world in Minecraft." Researchers found that the information provided by users was accurate 88 percent of the times. A portion of the inaccuracies can be attributed to people tweeting when traveling.



Public health officials could capture state-level information , or even better, for 15% of tweets. This is a good sign for the potential of a Twitter-based disease surveillance system to augment the data that has been confirmed from sentinel clinics.



"The first step is to search for posts about symptoms tied to actual location indicators and begin to plot them on the map," said Scott Burton, student at the graduate level and lead researcher of the study. "You might also want to look for posts that talk about actual diagnoses and not self-reported symptoms, such as "The doctor has told me I have the flu.'"



The computer scientists collaborated with two BYU health science professors for the project. Professor Josh West says speed is the primary benefit Twitter provides health officials.



"If people from a particular area are reporting similar symptoms on Twitter, public health officials could issue a notice for health professionals to be prepared for something," West said. "Under conditions such as that, it could be very useful."



Kesler Tanner, a BYU student, is the co-author of the study. Tanner was the one to write the code that allowed him to access the data through Twitter.  minecraft  is graduating in April and will be heading into graduate school to pursue a Ph.D.