Using Machine Learning to Establish the Concerns of Persons With HIV/AIDS During the COVID-19 Pandemic From Their Tweets

Richard K. Lomotey, Sandra Kumi, Maxwell Hilton, Rita Orji, Ralph Deters

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


There are millions of People Living with HIV/AIDS (PLWHA) globally and over the years, addressing their concerns has been topical for many stakeholders. It is a well-known and established fact that PLWHA are at increased risk of victimization and stigmatization. Unfortunately, the world experienced an outbreak of the COVID-19 pandemic that has led to strict social measures in many states. Thus, it is the goal of this research to study the impact that the outbreak and its mitigation measures have had on the PLWHA. Specifically, we sought to highlight their concerns from sentiments expressed on social media based on posted tweets. By combining machine learning (ML) techniques such as textual mining and thematic analysis, we determined 14 major themes as factors that are worth exploring. In this work, we originally extracted 2,839,091 tweets related to HIV/AIDS posted from March 2020 to April 2022. After initially doing data cleaning and preprocessing, we performed topic modeling using the Latent Dirichlet Allocation (LDA) topic model to extract 25 topics that are made up of 30 keywords each. The topics were then narrowed into 14 themes. The paper details the negative, positive, and neutral sentiment polarities which we highlight as concerning. These sentiments were determined using the Valence Aware Dictionary and sEntiment Reasoner (VADER) Sentiment Analysis Library with a 90% F1-score compared to TextBlob which showed a 53% F1-score. The research findings highlight issues affecting PLWHA during and post-pandemic such as high cost of medical care, late diagnosis of HIV, limited access to medications, stigmatization and victimization, absence of testing kits in hospitals, and lack of urgency in the development of vaccines or cure for HIV.

Original languageEnglish (US)
Pages (from-to)37570-37601
Number of pages32
JournalIEEE Access
StatePublished - 2023

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Materials Science
  • General Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Using Machine Learning to Establish the Concerns of Persons With HIV/AIDS During the COVID-19 Pandemic From Their Tweets'. Together they form a unique fingerprint.

Cite this