JMIR Publications

ABSTRACT

Background:

Pre-exposure prophylaxis (PrEP) is highly effective at preventing the acquisition of Human Immunodeficiency Virus (HIV). There is a substantial gap, however, between the number of people in the United States who have indications for PrEP and the number of them who are prescribed PrEP. While Twitter content has been analyzed as a source of PrEP-related data (e.g., barriers), methods have not been developed to enable the use of Twitter as a platform for implementing PrEP-related interventions.

Objective:

Men who have sex with men (MSM) are the population most affected by HIV in the United States. Therefore, the objective of this study was to develop and assess an automated natural language processing (NLP) pipeline for identifying men in the United States who have reported on Twitter that they are gay, bisexual, or MSM.

Methods:

Between September 2020 and January 2021, we used the Twitter Streaming Application Programming Interface (API) to collect more than 3 million tweets containing keywords that men may include in posts reporting that they are gay, bisexual, or MSM. We deployed handwritten, high-precision regular expressions on the tweets and their user profile metadata designed to filter out noise and identify actual self-reports. We identified 10,043 unique users geolocated in the United States, and drew upon a validated NLP tool to automatically identify their ages.

Results:

Based on manually distinguishing true and false positive self-reports in the tweets or profiles of 1000 of the 10,043 users identified by our automated pipeline, our pipeline has a precision of 0.85. Among the 8756 users for which a United States state-level geolocation was detected, 5096 (58.2%) of them are in the 10 states with the highest numbers of new HIV diagnoses. Among the 6240 users for which a county-level geolocation was detected, 4252 (68.1%) of them are in counties or states considered priority jurisdictions by the Ending the HIV Epidemic (EHE) initiative. Furthermore, the majority of the users are in the same two age groups as the majority of MSM in the United States with new HIV diagnoses.

Conclusions:

Our automated NLP pipeline can be used to identify MSM in the United States who may be at risk for acquiring HIV, laying the groundwork for using Twitter on a large scale to target PrEP-related interventions directly at this population.