Sentiments Analysis of Covid-19 Vaccine Tweets Using Machine Learning and Vader Lexicon Method

Abstract

The novel Coronavirus disease of 2019 (COVID-19) has subsequently named Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) have tormented the lives of millions of people worldwide. Effective and safe vaccination might curtail the pandemic. This study aims to apply the VADER lexicon, TextBlob and machine learning approach: to analyze and detect the ongoing sentiments during the affliction of the Covid-19 pandemic on Twitter, to understand public reaction worldwide towards vaccine and concerns about the effectiveness of the vaccine. Over 200000 tweets vaccine-related using hashtags #CovidVaccine #Vaccines #CornavirusVaccine were retrieved from 18 August 2020 to 20 July 2021. Data analysis conducted by VADER lexicon method to predict sentiments polarity, counts and sentiment distribution, TextBlob to determine the subjectivity and polarity, and also compared with two other models such as Random Forest (RF) and Logistic Regression (LR). The results determine sentiments that public have a positive stance towards a vaccine follows by neutral and negative. Machine learning classification models performed better than the VADER lexicon method on vaccine Tweets. It is anticipated this study aims to help the government in long run, to make policies and a better environment for people suffering from negative thoughts during the ongoing pandemic.