Author: Monselise, Michal; Chang, Chia-Hsuan; Ferreira, Gustavo; Yang, Rita; Yang, Christopher C
Title: Detecting Topics and Sentiments of Public Concerns on COVID-19 Vaccines with Social Media Trend Analysis. Cord-id: 10al0b04 Document date: 2021_9_17
ID: 10al0b04
Snippet: BACKGROUND As a number of vaccines for COVID-19 are given emergency use authorization by local health agencies and are being administered in multiple countries, it is crucial to gain public trust in these vaccines to ensure herd immunity through vaccination. One way to gauge public sentiment regarding the vaccines for the goal of increasing vaccination rates is by analyzing social media such as Twitter. OBJECTIVE The goal of this research is to understand public sentiment towards COVID-19 vaccin
Document: BACKGROUND As a number of vaccines for COVID-19 are given emergency use authorization by local health agencies and are being administered in multiple countries, it is crucial to gain public trust in these vaccines to ensure herd immunity through vaccination. One way to gauge public sentiment regarding the vaccines for the goal of increasing vaccination rates is by analyzing social media such as Twitter. OBJECTIVE The goal of this research is to understand public sentiment towards COVID-19 vaccines by analyzing discussions about the vaccines on social media for a period of sixty days when the vaccines were started in US. Using the combination of topic detection and sentiment analysis, we identify different types of concerns regarding vaccines that are expressed by different groups of the public that appear in social media. METHODS To better understand public sentiment, we collected tweets for exactly 60 days starting December 16th, 2020 that contained hashtags or keywords related to COVID-19 vaccines. We detected and analyzed the different topics of discussion of these tweets as well as their emotional content. Vaccine topics were identified using non-negative matrix factorization (NMF) and emotional content was identified using the VADER sentiment analysis library as well as using sentence BERT embeddings and comparing the embedding to different emotions using cosine similarity. RESULTS After removing all duplicates and retweets, 7,864,640 were collected during the time period. Topic modeling resulted in 50 topics of those we selected the 12 topics with the highest volume of tweets for analysis. Administration and access to vaccines are some of the major concerns in the pubic. Additionally, we classified the tweets in each topic into one of 5 emotions and found fear to be the leading emotion in the tweets followed by joy. CONCLUSIONS This research focuses not only on negative emotions that may lead to vaccine hesitancy but also on positive emotions toward the vaccine. By identifying both positive and negative emotions, we are able to identify the public's response to the vaccines overall and to news events related to the vaccines. These results are useful in developing plans for disseminating the authoritative health information and better communication to build understanding and trust.
Search related documents:
Co phrase search for related documents- Try single phrases listed below for: 1
Co phrase search for related documents, hyperlinks ordered by date