HIV-related tweeting: social media for HIV prevention?

Methods of using real-time social media technologies for detection and remote monitoring of HIV outcomes.

Young SD, Rivers C, Lewis B. Prev Med. 2014 Jun;63:112-5. doi: 10.1016/j.ypmed.2014.01.024. Epub 2014 Feb 8.

Objective: Recent availability of "big data" might be used to study whether and how sexual risk behaviors are communicated on real-time social networking sites and how data might inform HIV prevention and detection. This study seeks to establish methods of using real-time social networking data for HIV prevention by assessing 1) whether geolocated conversations about HIV risk behaviors can be extracted from social networking data, 2) the prevalence and content of these conversations, and 3) the feasibility of using HIV risk-related real-time social media conversations as a method to detect HIV outcomes.

Methods: In 2012, tweets (N=553 186 061) were collected online and filtered to include those with HIV risk-related keywords (e.g., sexual behaviors and drug use). Data were merged with AIDSVU data on HIV cases. Negative binomial regressions assessed the relationship between HIV risk tweeting and prevalence by county, controlling for socioeconomic status measures.

Results: Over 9 800 geolocated tweets were extracted and used to create a map displaying the geographical location of HIV-related tweets. There was a significant positive relationship (p<.01) between HIV-related tweets and HIV cases.

Conclusion: Results suggest the feasibility of using social networking data as a method for evaluating and detecting Human immunodeficiency virus (HIV) risk behaviors and outcomes.

 Abstract access  [1]

Editor’s notes: The concept of Big Data refers to data sets so large that they are almost or actually impossible to analyse or manage. Methods for harnessing big data sets, such as from social network sites online, are being developed for a variety of uses. These include understanding consumers for the purposes of building creative product marketing campaigns to predicting outbreaks of influenza. This paper examined the potential for using big data from Twitter to compare with areas of high HIV prevalence in the United States, to predict areas of increasing new HIV infections. There are several limitations for the method used in this paper. However, the idea presents an interesting concept. This study was conducted in a developed country, and while computers may not be readily available in resource limited settings, mobile phones are in use in most populations around the world. With mobile technology becoming increasingly sophisticated, and online social networking becoming more common, even in resource limited settings, this may be a strategy worth considering. It could be used in high HIV incidence networks within countries with high rates of HIV, especially in generalised epidemics. Clearly, this method will require additional research, validation and time to develop, but it could present a novel approach for estimating incidence without expensive testing. 

Epidemiology [4]
Northern America [5]
United States of America [6]
  • [7]