User description

According to new research by Brigham Young University, such tweets could be a boon for health officials who are trying to stop outbreaks. The study analyzed 24 million tweets from 10 million unique users. The study revealed that only 15% of tweets have precise location data. The data was gathered from user profiles and tweets that contain GPS data. This is likely to be a crucial mass for an early warning system that can detect terms such as "fever", "flu", and "coughing." Professor Christophe Giraud Carrier, BYU, stated that one of the things that this paper shows is that the distributions of tweets are roughly the same as the distributions of the population. This allows us to get an accurate representation of the country. "That's an additional good reason to be able to prove that it's valid, especially if you're going to study things like diseases spreading." Professor Giraud-Carrier (@ChristopheGC) and his computer science students from BYU discuss their findings in the latest issue of the Journal of Medical Internet Research. The researchers found surprisingly less data than they expected from Twitter's feature which allows tweets to be tagged with the location. They found that only 2 percent of tweets contained the GPS information. That's a much lower rate than what Twitter users have reported in surveys. "There is this gap that is well-known between what you think you are doing and what you are actually doing," Giraud-Carrier said. User profiles can often be used to search and analyze information about location. Of course, some people utilize that location field for an amusing joke, i.e. "Somewhere in my imagination" or "a cube world in Minecraft." Minecraft Textures Researchers found that the user-supplied data was correct 88 percent of times. Besides the jokes, a portion of the inaccurate data is due to people tweeting while they travel. The net result is that public health officials will be able to gather state-level information, or even better yet, 15 percent of tweets. This is a good sign for the viability and feasibility of a Twitter-based system for monitoring diseases to complement the data that has been confirmed from hospitals with sentinel surveillance. Scott Burton, a graduate student who was the lead researcher in the study, said that "the first step is to search for symptoms that are tied to location indicators" and then plot them on maps. "You can also find out if people are discussing actual diagnoses or self-reported symptoms like 'The doctor said I'm suffering from the flu.' Two BYU health science professors worked on the project along with computer scientists. Professor Josh West claims that Twitter's principal benefit for health officials is speed. West has stated that health officials could issue a warning to health professionals for those living in a specific area are sharing similar symptoms via Twitter. "Under circumstances like that, it could be very useful." BYU undergraduate Kesler Tanner is a co-author on the study. He created the code to get the data from Twitter. Minecraft Textures When his graduation is in April, he'll head off to graduate school to get a Ph.D.