AI-based study of social media maps SARS-CoV-2 vaccine hesitancy across the US

NewsGuard 100/100 Score

The unprecedented speed with which a new class of mRNA severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccine has been developed, trialed, approved and rolled out has left many in awe. But it has also left many unnerved.

Resistance to SARS-CoV-2 vaccines over concerns about their efficacy and safety has been reported all over the world but is thought to be particularly pronounced in the United States, where the anti-vaccine lobby has historically been large.

In May 71% of US adults indicated that they would definitely or probably obtain a vaccine to prevent COVID-19 if it were available. The percentage dropped sharply, however, to 51% in September. The survey shows that the US public is concerned about the safety and effectiveness of possible vaccines, and the pace of the approval process.”

Pew Research Center study, 2020

A team of researchers from the University of Rochester, New York, has produced an AI-based study that analyzes the social media platform Twitter to gauge public opinions in the US surrounding SARS-CoV-2 vaccines. Their findings have been released on the preprint medRxiv* server.

This news article was a review of a preliminary scientific report that had not undergone peer-review at the time of publication. Since its initial publication, the scientific report has now been peer reviewed and accepted for publication in a Scientific Journal. Links to the preliminary and peer-reviewed reports are available in the Sources section at the bottom of this article. View Sources

What are vaccines and how do they work?

Vaccines work by gently introducing a person’s immune system to an antigen – a pathogen or part of a pathogen that registers to the host as potentially threatening – which then induces the immune system to produce neutralizing antibodies against it. These antibodies then linger, ready to strike if the host encounters the pathogen out in the community.

Traditionally, vaccines have worked by introducing the host to a closely related pseudovirus or an inactivated or attenuated version of the wild-type virus. In the case of the Pfizer and Moderna candidates, however, a new type of vaccine has been developed in a staggering feat of nanotechnological innovation. These vaccines contain a small fragment of the SARS-CoV-2’s mRNA – its genetic material – that encodes for the spike protein (or S protein). The S protein is part of the virus that facilitates its entry into host cells and is the protruding, crown-like spike that lines the SARS-CoV-2 microbe (whence the coronavirus family derives its name).

With the Pfizer and Moderna candidates, the mRNA is encased in a lipid envelope and administered to the individual by intra-muscular injection (i.e., a 'jab' or 'shot'). As the S protein is the part of the virus that allows it to infiltrate and infect human cells, this has been a common target of much vaccine and antiviral therapeutic research.

While they can immunize vulnerable individuals against a targeted pathogen, the ultimate aim of a vaccine is to promote ‘herd immunity’ among a population. This is where enough people have a robust presence of antibodies in their system to prevent infection and thus cause chains of transmission to break down – significantly reducing the chances of vulnerable individuals from being infected.

For vaccines to be effective, they rely on mass compliance. Because vaccine hesitancy thus poses a threat to public health, it has been cited by the World Health Organization (WHO) – alongside air pollution and antimicrobial resistance – as a major public health risk currently facing humanity.

Using mathematical modeling, different researchers have projected different threshold requirements for herd immunity to be achieved, but all agree that a large majority of a given population needs to be administered for any of the vaccines to work.

The study

The researchers of the present study adopted a human-guided machine-learning framework – using more than 40,000 rigorously selected tweets from more than 20,000 distinct Twitter users from September to November of 2020 – to capture public opinions on the potential vaccines for SARS-CoV-2. They then classified the data into three groups: "pro-vaccine, vaccine-hesitant, and anti-vaccine."

The team also aggregated opinions at the state and national levels, finding that “major changes in the percentages of different opinion groups roughly correspond to major pandemic-related events.”

“Interestingly, the percentage of the pro-vaccine group is lower in the Southeast part of the United States,” they noted.

State-level public opinions about potential COVID-19 vaccines.
State-level public opinions about potential COVID-19 vaccines.

They also compared demographic factors like social capital, income, religious status, political affiliations, geolocations, sentiment of personal pandemic experience and non-pandemic experience, and county-level pandemic severity perception of these three groups to investigate the scope and causes of public opinions on vaccines. In doing so, they observed that socioeconomically disadvantaged groups were more likely to hold polarized opinions on vaccine candidates. The anti-vaccine opinion was strongest among those who had the worst personal pandemic experience.

Conclusion

Through counterfactual analyses, the researchers suggest that the “US public is most concerned about the safety, effectiveness, and political issues regarding potential vaccines for COVID-19, and improving personal pandemic experience increases the vaccine acceptance level.”

As the researchers themselves note, vaccine hesitancy is often a product of various context-specific factors and differs depending on the vaccine candidate and the pathogen in question. However, shedding more light by way of empirical data can clarify, as this study shows, those specific factors that can drive a drop in public confidence to an alarming level.

Given the public health risks associated with vaccine hesitancy, research of this sort could potentially help policymakers and public health authorities develop targeted and effective campaigns to allay public concerns about vaccines and their safety. Moreover, as the researchers note, these approaches can also help steer distribution and allocation policies when the time comes for the state to begin widescale administration.

This news article was a review of a preliminary scientific report that had not undergone peer-review at the time of publication. Since its initial publication, the scientific report has now been peer reviewed and accepted for publication in a Scientific Journal. Links to the preliminary and peer-reviewed reports are available in the Sources section at the bottom of this article. View Sources

Journal references:

Article Revisions

  • Apr 3 2023 - The preprint preliminary research paper that this article was based upon was accepted for publication in a peer-reviewed Scientific Journal. This article was edited accordingly to include a link to the final peer-reviewed paper, now shown in the sources section.
Dan Hutchins

Written by

Dan Hutchins

Dan graduated from Oxford Brookes University with a BA in History and Politics and the University of Cambridge with an MPhil in Political Thought and Intellectual History. He has a professional background in scholarly and non-fiction publishing, working in editorial both on the history list at Bloomsbury Publishing Plc and within the major reference division at the Royal Pharmaceutical Society.  He has wide interdisciplinary interests, particularly where the humanities and the natural sciences intersect, but is above all exercised by the human capacity to construct and tell stories out of a complex world – and this is exactly what brings him to AzoNetwork. In his spare time, Dan is an avid reader of both fiction and non-fiction, a keen walker and a hobbyist screenwriter.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Hutchins, Dan. (2023, April 03). AI-based study of social media maps SARS-CoV-2 vaccine hesitancy across the US. News-Medical. Retrieved on April 25, 2024 from https://www.news-medical.net/news/20201215/AI-based-study-of-social-media-maps-SARS-CoV-2-vaccine-hesitancy-across-the-US.aspx.

  • MLA

    Hutchins, Dan. "AI-based study of social media maps SARS-CoV-2 vaccine hesitancy across the US". News-Medical. 25 April 2024. <https://www.news-medical.net/news/20201215/AI-based-study-of-social-media-maps-SARS-CoV-2-vaccine-hesitancy-across-the-US.aspx>.

  • Chicago

    Hutchins, Dan. "AI-based study of social media maps SARS-CoV-2 vaccine hesitancy across the US". News-Medical. https://www.news-medical.net/news/20201215/AI-based-study-of-social-media-maps-SARS-CoV-2-vaccine-hesitancy-across-the-US.aspx. (accessed April 25, 2024).

  • Harvard

    Hutchins, Dan. 2023. AI-based study of social media maps SARS-CoV-2 vaccine hesitancy across the US. News-Medical, viewed 25 April 2024, https://www.news-medical.net/news/20201215/AI-based-study-of-social-media-maps-SARS-CoV-2-vaccine-hesitancy-across-the-US.aspx.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment
Post

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
Study reveals how SARS-CoV-2 hijacks lung cells to drive COVID-19 severity