Analyzing the Impact of Sentiments of Scientific Articles on COVID-19 Vaccination Rates

TL;DR

This study investigates how the sentiment of scientific articles about COVID-19 vaccines correlates with vaccination rates in the US, using sentiment analysis techniques, and finds only a weak correlation.

Contribution

It applies lexicon-based sentiment analysis to scientific articles and examines their impact on vaccination rates, providing insights into information influence during a pandemic.

Findings

Weak correlation between article sentiment and vaccination rate changes

Sentiment analysis performed using VADER on scraped article content

Study focused on US COVID-19 vaccination data

Abstract

At the peak of the COVID-19 pandemic, numerous countries worldwide sought to mobilize vaccination campaigns in an attempt to curb the spread and number of deaths caused by the virus. One avenue in which information regarding COVID vaccinations is propagated is that of scientific articles, which provide a certain level of credibility regarding this. Hence, this increases the probability that people who view these articles would get vaccinated if the articles convey a positive message on vaccinations and conversely decreases the probability of vaccinations if the articles convey a negative message. This being said, this study aims to investigate the correlation between article sentiments and the corresponding increase or decrease in vaccinations in the United States. To do this, a lexicon-based sentiment analysis was performed in two steps: first, article content was scraped via a Python library called BeautifulSoup, and second, VADER was used to obtain the sentiment analysis scores for each article based on the scraped text content. Results suggest that there was a relatively weak correlation between the average sentiment score of articles and the corresponding increase or decrease in COVID vaccination rates in the US.