Sentiment Analysis of COVID-19 Vaccine-related Twitter Data
Link to Medium article: https://towardsdatascience.com/covid-19-vaccine-whats-the-public-sentiment-7149c9b42b99
The COVID-19 pandemic has presented itself as one of the gravest global threats, and is still very much an ongoing menace.
In equal measure, we are in the midst of the biggest vaccination campaign in human history. According to Bloomberg, >65.6 million doses in 56 countries have been administered so far (as of 25 Jan 2020), translating to a staggering 3.4 million doses daily.
While the vaccine has offered renewed hope in the fight against COVID-19, it has also ignited aggressive anti-vaccine movements. Hence, it would be interesting to gauge the general public's perception towards COVID-19 vaccines using sentiment analysis (in Python) on recent Twitter data.
-
This repository contains the Jupyter notebook detailing the following aspects
- Setup of Twitter API
- Extracting and Pre-Processing Tweets
- Sentiment Analysis with NLTK Vader
- Sentiment Analysis with TextBlob
- Sentiment Analysis with Stanza
- Sentiment Analysis with FlairNLP
- Sentiment Analysis with Stanford CoreNLP
- Insights from Sentiment Analyses (Comparison of Results)
- Compound Sentiment with Ensemble Method (Average Scoring and Max Voting)
-
For the full write-up, do check out the Medium article for this project: https://towardsdatascience.com/covid-19-vaccine-whats-the-public-sentiment-7149c9b42b99