Elsevier

Vaccine

Volume 39, Issue 39, 15 September 2021, Pages 5499-5505
Vaccine

Public attitudes toward COVID-19 vaccines on English-language Twitter: A sentiment analysis

https://doi.org/10.1016/j.vaccine.2021.08.058Get rights and content

Highlights

  • Public sentiment on COVID-19 vaccines varied significantly over time and geography.

  • Sentiment analysis is an effective way to gain insight into the public's sentiment towards the covid-19 vaccine.

  • Twitter has become an important platform for gathering public opinion.

Abstract

Objective

To identify themes and temporal trends in the sentiment of COVID-19 vaccine-related tweets and to explore variations in sentiment at world national and United States state levels.

Methods

We collected English-language tweets related to COVID-19 vaccines posted between November 1, 2020, and January 31, 2021. We applied the Valence Aware Dictionary and sEntiment Reasoner tool to calculate the compound score to determine whether the sentiment mentioned in each tweet was positive (compound ≥ 0.05), neutral (-0.05 < compound < 0.05), or negative (compound ≤ -0.05). We applied the latent Dirichlet allocation analysis to extract main topics for tweets with positive and negative sentiment. Then we performed a temporal analysis to identify time trends and a geographic analysis to explore sentiment differences in tweets posted in different locations.

Results

Out of a total of 2,678,372 COVID-19 vaccine-related tweets, tweets with positive, neutral, and negative sentiments were 42.8%, 26.9%, and 30.3%, respectively. We identified five themes for positive sentiment tweets (trial results, administration, life, information, and efficacy) and five themes for negative sentiment tweets (trial results, conspiracy, trust, effectiveness, and administration). On November 9, 2020, the sentiment score increased significantly (score = 0.234, p = 0.001), then slowly decreased to a neutral sentiment in late December and was maintained until the end of January. At the country level, tweets posted in Brazil had the lowest sentiment score of −0.002, while tweets posted in the United Arab Emirates had the highest sentiment score of 0.162. The overall average sentiment score for the United States was 0.089, with Washington, DC having the highest sentiment score of 0.144 and Wyoming having the lowest sentiment score of 0.036.

Conclusions

Public sentiment on COVID-19 vaccines varied significantly over time and geography. Sentiment analysis can provide timely insights into public sentiment toward the COVID-19 vaccine and guide public health policymakers in designing locally tailored vaccine education programs.

Cited by (0)

View Abstract