Saleh, S. N., McDonald, S. A., Basit, M. A., Kumar, S., Arasaratnam, R. J., Perl, T. M., ... & Medford, R. J. (2021). Public Perception of COVID-19 Vaccines through Analysis of Twitter Content and Users. medRxiv. https://www.medrxiv.org/content/10.1101/2021.04.19.21255701v1

University of Michigan - Ann Arbor

Researchers were interested in conducting content and sentiment analyses of tweets to study public perceptions for different users regarding COVID-19 vaccines. 

Public Perception of COVID-19 Vaccines through Analysis of Twitter Content and Users

Content analysis 
- Cross-sectional observational study
- Used Snscrape library to get tweets from February 1st to December 11th, 2020 that contain the keywords “covid” or “coronavirus” and “vaccine”
- Used natural language processing to analyze tweet content – focused on 300 most commonly mentioned terms

Sentiment analysis 
- Used Valence Aware Dictionary and Sentiment Reasoner (VADER) for determining sentiments behind tweets. Vader provides a normalized, weighted composite score, taking into account emojis, punctuations, and syntax in addition to pure text. A score that is larger than or equal to 0.05 is considered positive sentiment, otherwise it is of negative sentimental rating. 
- Used Mann-Kendall trend test and TextBlob library to rate tweets on a scale of objective (0) to subjective (1)
- Used NRCLex library to match specific words in tweets to emotions

Topic modeling
- Used Correlation Explanation (CorEx) to identify 20 topic clusters and determine which of the topics were most informative
- Picked 15 topics for the model with highest correlation to the tweets 

User demographics	
- Obtained user information including account setup date, followers, follows, posts, likes, descriptions, verified status
- Used m3inference library to make predictions about whether the accounts were from organizations or individuals
- Used Mann-Whitney U and Chi-squared tests for significance 

Public Perception of COVID-19 Vaccines through Analysis of Twitter Content and Users Methodology

- Overall, there were significantly more tweets associated with positive than negative sentiments and the main emotion associated with the tweets was trust 
- Tweets from individual accounts contained more fear and less anticipation and trust compared to organizational accounts 
- Women showed more fear and less anticipation
- Users over the age of 40 were more fearful and put less trust in the vaccines and vaccine development
- 20% of the tweets contained elements of fear towards getting the vaccine, even though there are a lot more tweets with positive sentiments and the emotion of trust 

Learn Before

Related