Sentiment Analysis of Covid Vaccine Tweet with Vader, and Implementation of Different Machine Learning Models

Sentiment analysis, referred to as opinion mining, is a natural language processing (NLP) technique that indicates a document's emotional tone. Since Covid-19 epidemic, there has been a lot of talk on social media and news sites about the necessity for a COVID-19 vaccine. However, the general public has expressed their concerns of vaccines security and efficacy on social media websites like Twitter. Using the Twitter API, these tweets are gathered from Twitter. For this research, we are using the Natural Language Toolkit (NLTK) for analyzing opinions expressed in tweets associated to covid vaccine utilizing the vocabulary- and rule-based sentiment analysis tool VADER (Valence Aware Dictionary for Sentiment Reasoning), which has been specially designed to analyze sentiments from social media. The dataset is converted into TF-IDF vectorization and the model was trained using different classifiers. We compared different ML applications and got our highest accuracy with Linear SVC with L1-based feature selection.