This project seeks to increase public confidence in the COVID-19 vaccine. By harnessing the power of data science and artificial intelligence, it will develop evidence-based public messaging that encourages vaccination, in partnership with local public health departments.
Nearly a year into the global COVID-19 pandemic, we have reached a critical moment where several vaccines have been approved for use, and the possibility of curbing the spread of the virus is within reach if enough individuals are vaccinated. Over the past two decades, an increasing proportion of the population has come to view vaccines with skepticism, and in many cases, refrained from getting vaccinated altogether. While the procedural, behavioral and access barriers to vaccine uptake have been studied extensively, the emotional, ideological and rhetorical bases for vaccine hesitancy are poorly understood. This limited understanding, combined with public distrust in science and government, is likely to undermine efforts to robustly and quickly vaccinate against COVID-19.
The project will engage literary scholars, medical professionals, data scientists, political scientists, community leaders and public health officials. It will create the world’s largest public dataset of vaccine-hesitant language in English, collected from online forums such as Facebook, YouTube and Twitter, which have become primary platforms for discussing and disseminating vaccine skepticism and other vaccine-related concerns. Leveraging the power of such collected data, the project will use artificial intelligence to develop public messaging that reflects the ways in which people express specific forms of hesitancy. This approach represents a significant effort to use AI to analyze the language of vaccine hesitancy and then use that language to combat vaccine skepticism.
Rishi K. GoyalColumbia UniversityProject LeadRead Full Bio arrow_right_alt
Rishi Goyal is Director, Medical Humanities Assistant Professor of Emergency Medicine at the Columbia University Medical Center (in Medical Humanities and Ethics and the Institute for...
Dennis Yi TenenColumbia UniversityProject LeadRead Full Bio arrow_right_alt
Dennis Yi Tenen is an associate professor of English Literature, Digital Humanities, and New Media Studies at Columbia University. A long-time affiliate of Columbia’s Data Science Institute...
Noémie ElhadadColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Dr. Noémie Elhadad is an Associate Professor of Biomedical Informatics, affiliated with Computer Science and the Data Science Institute at Columbia University.
Arden HegeleColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Arden Hegele, PhD, is a Medical Humanities Fellow and literary scholar at Columbia University. She teaches on the Morningside campus in the Department of English and Comparative Literature...
Kathleen R. McKeownColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Kathleen R. McKeown is the Henry and Gertrude Rothschild Professor of Computer Science at Columbia University and the Founding Director of the Data Science Institute, serving as Director...
Sarah MonksColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Sarah Monks is Assistant Director of the Institute for Comparative Literature & Society, Columbia University. She graduated from the University of Arizona with a BA in Psychology and Sociology.
Moacir P. de Sa PereiraColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Moacir P. de Sá Pereira (he/him/his) is the Research Data Librarian at Columbia University Libraries. A scholar of literature and space, he taught at New York University, Vilnius Gediminas...
Melissa StockwellColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Dr. Stockwell is Chief of the Division of Child and Adolescent Health and an Associate Professor of Pediatrics (Vagelos College of Physicians and Surgeons) and Population and Family Health...
Prerna SinghBrown UniversityProject TeamRead Full Bio arrow_right_alt
Prerna Singh is Mahatma Gandhi Associate Professor of Political Science and International Studies at Brown University with appointments in the Department of Behavioral and Social...
Jeremiah Trinidad-ChristensenColumbia UniversityProject TeamRead Full Bio arrow_right_alt
Jeremiah Trinidad-Christensen (he/him/his) is the Head of the Research Data Services at Columbia University Libraries. Prior to this he was the GIS Librarian, where he was hired to create...
Mass vaccination will be the most important strategy for minimizing morbidity and mortality from COVID-19 and diminishing its devastating consequences.
Over the past two decades, an increasing proportion of the population has come to view vaccines with skepticism – leading a growing number of people to reject getting vaccines altogether. In 2019 the World Health Organization listed “vaccine hesitancy,” defined as a delay in acceptance or refusal of vaccines despite availability of vaccination services, as one of the top ten threats to global health. The rise in vaccine hesitancy risks reversing the significant progress made toward eradicating certain diseases – a threat heightened by the politicization of the COVID-19 pandemic.
According to recent polls, approximately four in 10 people in the United States would be unwilling to get a COVID-19 vaccine. While the procedural, behavioral and access barriers to vaccine uptake have been studied extensively, the emotional, ideological and rhetorical bases for vaccine hesitancy are poorly understood. This limited understanding, combined with growing public distrust in science, is likely to undermine efforts to vaccinate against COVID-19. Additionally, COVID-19 vaccines may foster new concerns and forms of hesitancy because of the speed of the rollout (“Operation Warp Speed”) and the fact that multiple vaccines are being distributed at the same time.
Social media plays a significant role in spreading misinformation and disinformation about vaccines, driven by both anti-vaccination advocates and by bots and trolls designed to amplify discord. Online forums such as Facebook, YouTube and Twitter have become primary platforms for discussing and disseminating vaccine-related concerns. Yet current efforts to combat vaccine hesitancy do not sufficiently take into account the growing role that social media and the conversations on these platforms play in spreading such skepticism. Efforts to combat vaccine hesitancy continue to use medical and scientific experts, politicians and community leaders to spearhead messaging campaigns that focus on science, safety and efficacy. While important, these approaches do not address the contextual basis of vaccine hesitancy or speak its language, and therefore have largely failed to win over dubious populations. A sustained and empirical effort to understand vaccine hesitancy can help to inform more effective campaigns to increase vaccine confidence.
The project will partner with the Maine Department of Health and Human Services and Ulster County in New York State to develop, administer and measure the efficacy of a public messaging campaign informed by the insights gained through research and analysis of online vaccine hesitancy forums.
If successful, this project will help increase confidence in a COVID-19 vaccine among the public in Maine and Ulster County, and model an approach that could be adopted by other local, state and federal officials. More broadly, the approach could elevate the role of data, rather than intuition, in driving public health messaging; validate a user-centered design approach that seeks to understand and address the underlying concerns of citizens with respect to vaccines and public health; and demonstrate how technology can be harnessed to address some of the problems that it has exacerbated.