Twitter Sentiment Analysis towards COVID-19 Vaccines: A Case Study in New York City

Abstract

According to the World Health Organization report in 2019, the COVID-19 vaccine hesitancy was one of the major threats to global health. Therefore, the study of vaccine-related conversations on social media could help governments or vaccine providers around the world perceive the current public’s outlook and emotion, which heavily contributes to their confidence in the vaccination process. In this paper, we collected the vaccine-related tweets from New York City using the longitude and latitude configuration. The pre-processing technique was applied in order to categorise them into three sentiment types: positive, negative, and neutral. After that, the training and testing dataset were proportionally generated. Different machine learning techniques, which included Logistic Regression (LR), Naive Bayes, Support Vector Machine (SVM), Decision Trees, Random Forest and Multi-Layer Perceptron (MLP), were then utilised on our dataset to obtained the results. The comparison showed that the highest accuracy of 93.63 percent was achieved using MLP, while Naive Bayes produced the lowest accuracy of 82.13 percent. In conclusion, the promising finding of this study suggests that the application of Sentiment Analysis on social media platform can be used to determine the public’s general opinion regarding the COVID-19 vaccines.