Researchers from UCLA (Univeristy of California, Los Angeles) looked at more than 550 million geo-located tweets from May 2012 to December 2012. The twitter study which was published in the peer-reviewed journal Preventive Medicine, discusses that it may be possible to predict sexual risk and drug use behaviors by monitoring tweets shared on the popular social networking site. The process also included mapping where those tweets come from and linking them with data on the geographical distribution of HIV cases. Twitter just got REAL guys.
Who would have ever thought that tweets including the words “sex” and “get high” could provide such information? The researchers created an algorithm (a process or set of rules to be followed in calculations or other problem-solving operations) to scan tweets that suggested risky behavior. Words like “sex” and “get high” were amongst others that appeared in the scan.
Shared in the report by Preventive Medicine, it was said: “When the researchers linked the tweets to data on HIV cases, they found a significant relationship between those indicating risky behavior and counties where the highest numbers of HIV cases were reported.”
Sean Young, co-director of the Center for Digital Behavior at UCLA and the assistant professor of family medicine at the David Geffen School of Medicine at UCLA explains: “Ultimately, these methods suggest that we can use ‘big data’ from social media for remote monitoring and surveillance of HIV risk behaviors and potential outbreaks.”
Here are the top four states with the most geo-located tweets. These tweets include both general statements made towards risky behavior and HIV related information:
1.California (9.4 percent)
2. Texas (9.0 percent)
3. New York (5.7 percent)
4. Florida (5.4 percent)
The geographical data on HIV cases that UCLA researchers used was from 2009. Tweets found were linked to AIDSVu.org, an interactive online map that illustrates the prevalence of HIV in the U.S. Since the mapping data is outdated, researchers see that as a weakness in the study and they follow by saying “In order to test if this approach can be used to predict future behaviors and outbreaks there is a need for a “gold standard” of frequently updated data.”
Do you think that if the mapping data was current, the tracking of HIV would still be possible?