Using Twitter Data to Understand Public Perceptions of Approved versus Off-label Use for COVID-19-related Medications
Not on the map. Why?
Abstract (arXiv)
Understanding public discourse on emergency use of unproven therapeutics is crucial for monitoring safe use and combating misinformation. We developed a natural language processing-based pipeline to comprehend public perceptions of and stances on coronavirus disease 2019 (COVID-19)-related drugs on Twitter over time. This retrospective study included 609,189 US-based tweets from January 29, 2020, to November 30, 2021, about four drugs that garnered significant public attention during the COVID-19 pandemic: (1) Hydroxychloroquine and Ivermectin, therapies with anecdotal evidence; and (2) Molnupiravir and Remdesivir, FDA-approved treatments for eligible patients. Time-trend analysis was employed to understand popularity trends and related events. Content and demographic analyses were conducted to explore potential rationales behind people's stances on each drug. Time-trend analysis indicated that Hydroxychloroquine and Ivermectin were discussed more than Molnupiravir and Remdesivir, particularly during COVID-19 surges. Hydroxychloroquine and Ivermectin discussions were highly politicized, related to conspiracy theories, hearsay, and celebrity influences. The distribution of stances between the two major US political parties was significantly different (P < .001); Republicans were more likely to support Hydroxychloroquine (55%) and Ivermectin (30%) than Democrats. People with healthcare backgrounds tended to oppose Hydroxychloroquine (7%) more than the general population, while the general population was more likely to support Ivermectin (14%). Our study found that social media users have varying perceptions and stances on off-label versus FDA-authorized drug use at different stages of COVID-19. This indicates that health systems, regulatory agencies, and policymakers should design tailored strategies to monitor and reduce misinformation to promote safe drug use.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 16 of its 61 references that are in the map. First posted on arXiv 29 Jun 2022.
Builds on
16 of 61 references.
References · 16
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
- 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
- 2022TimeLMs: Diachronic Language Models from Twittercited by 129
- 2019Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootingscited by 67
- 2020The COVID-19 Social Media Infodemiccited by 64
- 2019Demographic Inference and Representative Population Estimates from Multilingual Social Media Datacited by 24
- 2018Me, My Echo Chamber, and I: Introspection on Social Media Polarizationcited by 20
- 2021COVID-19 Vaccine Hesitancy on Social Media: Building a Public Twitter Dataset of Anti-vaccine Content, Vaccine Misinformation and Conspiraciescited by 17
- 2020A Stance Data Set on Polarized Conversations on Twitter about the Efficacy of Hydroxychloroquine as a Treatment for COVID-19cited by 12
- 2020Cross-language sentiment analysis of European Twitter messages duringthe COVID-19 pandemiccited by 11
- 2022Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysiscited by 9
- 2021Analysis of the influence of political polarization in the vaccination stance: the Brazilian COVID-19 scenariocited by 5
4 more
- 2020Face Off: Polarized Public Opinions on Personal Face Mask Usage during the COVID-19 Pandemiccited by 3
- 2021Engaging Politically Diverse Audiences on Social Mediacited by 3
- 2020The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemiccited by 2
- 2022Understanding Public Opinion on Using Hydroxychloroquine for COVID-19 Treatment via Social Mediacited by 2
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 3; 2025: 3; 2026: 1.
8 papers.
- 2024Large Language Models in Mental Health Care: a Scoping Reviewcited by 34
- 2022METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweetscited by 12
- 2024Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI modelscited by 1
- 2025Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfactioncited by 1
- 2025Crowdsourcing-Based Knowledge Graph Construction for Drug Side Effects Using Large Language Models with an Application on Semaglutidecited by 1
- 2024Mpox Narrative on Instagram: A Labeled Multilingual Dataset of Instagram Posts on Mpox for Sentiment, Hate Speech, and Anxiety Analysiscited by 0
- 2025Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Modelscited by 0
- 2026Geospatial AI, Dataverse Metadata, and the Study of Place-Based Governmentcited by 0
- 2026Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government10 Sep 2026
- 2025Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Models2 May 2025
- 2025Crowdsourcing-Based Knowledge Graph Construction for Drug Side Effects Using Large Language Models with an Application on Semaglutide6 Apr 2025
- 2025Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfaction26 Mar 2025
- 2024Mpox Narrative on Instagram: A Labeled Multilingual Dataset of Instagram Posts on Mpox for Sentiment, Hate Speech, and Anxiety Analysis9 Sep 2024
- 2024Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models24 Jun 2024
- 2024Large Language Models in Mental Health Care: a Scoping Review1 Jan 2024
- 2022METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets28 Sep 2022