Abstract

Over the past 100 years, epidemiological models have evolved to incorporate greater facets of the process. With the advent of social networking, massive computational power, population sentiment analysis can now be added to the epidemiological modeling process. Sentiment analysis is greater understanding of the fears, uncertainties, motivation, and trends of the public with respect to vaccination and associated events. Lack of public confidence in the efficacy of models, safety of vaccines, and appropriateness of policies confounds vaccine inoculation prediction. Sentiment analysis of social media is a seminal technique that accesses shared users' contents and tweets on the Twitter platform for daily fast and accurate modeling of public sentiment. As an applied contribution to this science, we present sentiment-based models for predicting United States daily COVID-19 vaccine inoculations. The research methodology encompasses predictive regression models spanning three phases of the U.S. pandemic including a baseline COVID-19 phase, a Delta variant phase, and Omicron variant phase that when combined span the period June 1, 2021, to March 31, 2022. Additionally, the models incorporate U.S. population behavior responses during the CDC recommended first dose interval, second dose interval, and booster intervals. Investigation of variables influencing daily inoculations identified CDC VOC phase, daily cases, daily deaths, and positive and negative Twitter Tweets as statistically significant for first dose and booster dose intervals exceeding a predictive R square of 77% and 84% respectively. The best regression model for the second dose interval proved to be a three variable- phases, cases, and negative tweets - inoculation model that exceeded a predictive R square of 53%. Limiting tweets collection to geolocated tweets does not encompass the entire U.S. Twitter population. However, Kaiser Family Foundation (KFF) surveys results appear to generally support the regression factors common to the First Dose and Booster Dose regression models and their results.

Notes

If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu

Graduation Date

2023

Semester

Spring

Advisor

Proctor, Michael

Degree

Doctor of Philosophy (Ph.D.)

College

College of Engineering and Computer Science

Department

Industrial Engineering and Management Systems

Degree Program

Industrial Engineering

Format

application/pdf

Identifier

CFE0009509; DP0027513

URL

https://purls.library.ucf.edu/go/DP0027513

Language

English

Release Date

May 2024

Length of Campus-only Access

1 year

Access Status

Doctoral Dissertation (Open Access)

Share

COinS