Classification of Covid-19 Vaccines tweets using Naïve Bayes Classification

Abstract

Recently COVID-19 has become the most discussed topic in different social media platforms like Twitter, Facebook, Instagram etc. As time moves on, lot of messages and videos are posted in social media. As expected, most of the public followed these messages and becomes panic because of lack of information, misinformation about COVID-19 and its impact. This research study proposes a Twitter sentiment analysisbased on the most popular vaccines Covaxin, Covishield, and Pfizer. Most of the people expressed their feelings about vaccines in the twitter. Twitter API authentication is used here to extract the tweets. These extracted tweets are difficult to analyze, hence pre-processing has been done i.e., unstructured data is converted into structured format. After completion of preprocessing, the data is further classified by using Naïve Bayes algorithm. This algorithm performs data classification and divides it into three major classes as positive, negative, and neutral. The result shows that the covaxin yields 48.36% positive, 35.6% negative, and 16.04% neutral, Covishield yields 44.25% positive, 39.67% negative, and 16.08% neutral, Pfizer yields 42.95% positive, 39.45% negative, and 17.6% neutral sentiment.