Sentiment Analysis of COVID-19 Vaccination Impact on Twitter Tweets Using NLP Supervised Learning and RNN Classification Comparison

Abstract

Twitter provides a platform for exchanging information and opinions on global concerns like the COVID-19 epidemic. During the COVID-19 pandemic, we used a collection of around 16,180 tweets to derive inferences regarding public views toward the vaccine impact once immunizations became widely available to the community. We use natural language processing and sentiment analysis techniques to uncover information regarding the public's perception of the COVID-19 vaccine. Our findings demonstrate that people are more pleased about taking COVID-19 shots than they are about some of the vaccines' side effects. We also look at people's reactions to COVID-19 safety measures after they have received the immunizations. In terms of maintaining safety precautions against COVID-19 among the vaccinated population, good attitude outnumbers negative emotion. We also estimate that around 48 percent of individuals have a neutral attitude, 36 percent have a positive opinion, and around 16 percent have a negative opinion towards vaccination. This research will help policymakers better assess public reaction and plan vaccination campaigns, as well as health and safety measures, amid the current global health crisis.