Previously submitted to: JMIR mHealth and uHealth (no longer under consideration since Jun 06, 2022)
Date Submitted: Nov 12, 2021
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Consumer Insights of COVID-19 Vaccines from Four Cities with Higher Percentages of African Americans to Inform Local Health Campaigns: Topic, Sentiment, and Textual Analyses
ABSTRACT
Background:
COVID-19 vaccination rates have waned across the country since the rollout in early 2021, especially among African American neighborhoods. Vaccine hesitancy is a recurring theme challenging the world’s public health. Yet, months after efforts to vaccinate the world’s population, we still do not have a good understanding of consumer insights about those who choose to be vaccinated and those who refuse. This also suggests that many vaccination campaigns are running on assumptions, not evidence-informed by consumer insights.
Objective:
The purpose of this study is to understand consumer insight of COVID-19 vaccines in Kansas City, a city with higher percentages of African Americans, to contextualize the insight and further compare data from Kansas City with insights from three other similar-sized towns (Long Beach, California; Omaha, Nebraska; Raleigh, North Carolina) that also have higher percentages of people of color.
Methods:
The researchers collected and analyzed 180,128 tweets from four cities. Triangulated methods were used to look at the breadth and depth of data to provide validity to the findings. In addition, health communication experts, informed by machine learning/deep learning topic and emotion models, conducted a textual analysis of the tweets. The strength of this study is the compilation of methods and the ways in which the data was analyzed and visualized.
Results:
Four major themes about COVID were discovered from the mass of tweets: “COVID Vaccines,” “Politics,” “Mitigation Measures,” and “Community/Local Issues.” The tweets per topic and emotion category were visualized to show regional differences and longitudinal changes. Critical moments of emotional changes were detected. Textual analysis based upon data partitioned by the models identified national and local themes. Insights into strategies of appealing to residents are discussed.
Conclusions:
This project’s data reveal wavering relationships of trust among residents and the government and its entities. While long-term initiatives should be used to rebuild and strengthen relationships among residents in cities with higher percentages of people of color, additional attention should be given to the health messaging directed at this audience. Practical implications are offered to inform local vaccination campaigns.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.