A new study suggests that social networking sites, such as Twitter, can be used to detect HIV risks and drug use-related behaviors, thus preventing them from spread and outbreak.
Researchers from the University of California concluded that through monitoring, mapping, and linking of tweets on the geographical distribution of HIV cases, sexual risks and drug abuse can be predicted. The use of prohibited drugs was found associated with HIV sexual risk behaviors and its transmission.
In the study, they used over 550 million tweets from May 26 to Dec. 9, 2012, and made an algorithm that would identify words and phrases that suggest sexually-risky and drug abuse behaviors. After that, they mapped the tweets' origin and ran statistical models to find if the tweets originated from places with high HIV cases.
The algorithm showed 8,538 tweets that suggest sexually risky behaviors. Of these, 9.4 percent is from California, nine percent is from Texas and 5.4 percent is from New York - the states with the most tweets. Tweets with drug use-related behavior contents totaled to 1,342.
The origin of tweets that suggest sexually risky behaviors were then linked to the 2009 geographical distribution of HIV cases from AIDSVu.Org, an interactive online map that shows the incidence of HIV in different states in the United States. After linking, they found that the area of risky tweets matches the location where the highest numbers of HIV cases were reported.
"Ultimately, these methods suggest that we can use 'big data' from social media for remote monitoring and surveillance of HIV risk behaviours and potential outbreaks," said Sean Young, assistant professor of family medicine at the David Geffen School of Medicine at UCLA and co-director of the Center for Digital Behaviour at UCLA to Business Standard.
"But this is the first to suggest that Twitter can be used to predict people's health-related behaviours and as a method for monitoring HIV risk behaviours and drug use," he added.
This study titled Methods of using real-time social media technologies for detection and remote monitoring of HIV outcomes was published in February on the journal Preventive Medicine.
