User description

According to a new study conducted by Brigham Young University, such tweets could be a boon for health officials who are trying to prevent outbreaks. The study sampled 24 million tweets from 10 million unique users. They discovered that accurate location information is available for around 15 percent of tweets (gathered from user profiles and tweets which contain GPS data). This is likely to be a critical mass for an early warning system that could detect terms such as "fever", "flu", and "coughing." Professor Christophe Giraud Carrier, BYU said that one of the things this paper illustrates is that the distributions of tweets are approximately the same as the distributions of people. This allows us to have an accurate representation of the country. "That's another good validity point especially if you wish to examine things such as diseases spreading." Professor Giraud-Carrier (@ChristopheGC) and his computer science students at BYU discuss their findings in a recent issue of the Journal of Medical Internet Research. Researchers discovered that Twitter's feature for location-tagging, which allows tweets to be tagged with the location was not as useful as they expected. They found that only 2 percent of tweets had the GPS information. This is much lower than the percentage Twitter users have reported in surveys. "There is this gap that is well known between what you think you are doing and what you're actually doing," Giraud-Carrier said. Location info can more often be found and extracted from profiles of users. Of course, there are some who use the location field to make humorous purposes, i.e. "Somewhere in my imagination" or "a cube world in Minecraft." Researchers have confirmed that the data provided by users was accurate 88 percent of the times. A portion of the inaccuracies result from people tweeting when traveling. Health officials from public health could collect state-level data or better than 15 percent of tweets. This bodes well for the viability and feasibility of a Twitter-based system of monitoring diseases to complement the confirmed data from sentinel hospitals. "The first step is to search for posts about symptoms tied to actual location indicators and start to plot points on the map," said Scott Burton, a graduate student and lead researcher of the study. " Need realtor should also see if people are discussing actual diagnosis or self-reported symptoms such as 'The doctor said I'm suffering from the flu.' Two BYU health science professors collaborated on the project along with computer scientists. Professor Josh West says speed is the primary benefit Twitter provides health officials. West said that public health officials could issue a warning to healthcare providers if people in a certain region are experiencing similar symptoms on Twitter. It could prove very useful in such situations. Kesler Tanner, a BYU student, is the co-author of the study. He wrote the code to obtain the data from Twitter. When his graduation is in April, he'll go off to graduate school to obtain the title of Ph.D.