Predicting COVID-19 Vaccination Uptake from Public Discourse: A Machine Learning Approach
2023 - 2026, funded by the Federal Excellence Initiative through the University of Hamburg
Through increasing population density and the encroachment of settlements on animal habitats, human societies are increasingly vulnerable to epidemics. Newly emerging epidemics can be countered through (i) the development of a vaccine or cure and (ii) its deployment to a sufficiently large part of the population. In the case of the COVID-19 pandemic, the development of effective vaccines was initially far from assured, but ultimately much faster and more successful than its deployment. This task, in turn, encountered important but addressable logistical challenges, but ultimately failed to convince a significant minority of the population to get vaccinated.
In this project, we will explore the relationship between public discourse and COVID-19 vaccination uptake and how to use real world data from Germany and England to identify public opinion on COVID-19 vaccination, with the ultimate aim of identifying strategies to increase the uptake of COVID-19 vaccinations. The analysis will apply big data and machine learning techniques to Twitter data and will link these to data on local vaccination rates. From a policy perspective, the output of this project can be used to inform public health response in real time in future pandemics.
At the heart of the proposal is an interdisciplinary approach, combining health economics and linguistics with new methods from data science. Our project will contribute to several key areas of the University of Hamburg: The core research area Infection Research, the emerging field Health Economics and the profile initiative Linguistic Diversity.
This project builds on the findings of the earlier project "The Impact of Public Discourse on Healthcare Utilization during the COVID-19 Pandemic"
More information available at:
https://www.hcds.uni-hamburg.de/cdls/project-hcds/predicting-covid-19.html