Mining Pre-Exposure Prophylaxis Trends in Social Media

Abstract

Pre-Exposure Prophylaxis (PrEP) is a ground-breaking biomedical approach to curbing the transmission of Human Immunodeficiency Virus (HIV). Truvada, the most common form of PrEP, is a combination of tenofovir and emtricitabine and is a once-daily oral mediation taken by HIV-seronegative persons at elevated risk for HIV infection. When taken reliably every day, PrEP can reduce one's risk for HIV infection by as much as 99%. While highly efficacious, PrEP is expensive, somewhat stigmatized, and many health care providers remain uninformed about its benefits. Data mining of social media can monitor the spread of HIV in the United States, but no study has investigated PrEP use and sentiment via social media. This paper describes a data mining and machine learning strategy using natural language processing (NLP) that monitors Twitter social media data to identify PrEP discussion trends. Results showed that we can identify PrEP and HIV discussion dynamics over time, and assign PrEP-related tweets positive or negative sentiment. Results can enable public health professionals to monitor PrEP discussion trends and identify strategies to improve HIV prevention via PrEP.