Date of Award

Spring 6-4-2023

Document Type

Thesis (Undergraduate)

Department

Quantitative Social Science

First Advisor

Soroush Vosoughi

Abstract

This thesis explores the dynamics of COVID-19 vaccination attitudes on Twitter across three specific events, focusing on changes observed within different racial groups. Understanding the shifts in public sentiment regarding COVID-19 vaccination is crucial for developing targeted interventions to improve vaccine uptake and decision-making among individuals from diverse racial backgrounds. To conduct this study, I first collected tweets from one month before and after each selected event. I built two machine learning classifiers to perform sentiment and emotion analysis on these collected tweets. Additionally, an AI facial recognition model was utilized to categorize Twitter users by race. This enabled the examination of sentiment and emotion patterns before and after the events across different racial groups. Lastly , a trigram analysis of the actual content of tweets within each racial group was conducted to identify and understand the prevalent topics of conversation. This analysis provided insights into the specific issues and concerns raised by different racial groups in relation to COVID-19 vaccination. The findings of this study contribute to a deeper understanding of the evolving attitudes towards COVID-19 vaccination on Twitter. By identifying changes in sentiment and emotion and exploring the topics of conversation, this research sheds light on the nuances and variations in vaccine-related discussions among different racial communities. These insights are crucial for the development of targeted interventions and strategies aimed at increasing vaccine uptake and addressing vaccine decision-making within specific racial groups.

Download

Share

COinS