Sentiment analysis for COVID-19 vaccination news

Abstract

In this digital era where information is widely available and easily retrievable from many different sources, large amount of unstructured data is generated every day. Social media, such as Facebook, Instagram or Twitter, provides a means for people around the world to create, share and exchange information and ideas in virtual communities and networks has embedded itself in a large percentage of human population’s everyday lives. In 2020, the outbreak of Covid-19 coronavirus has led to a sharp increase in the usage of social media and as such, news related to both the virus and its vaccines are generated in vast amounts daily. This provides opportunity for the data to be mined and turned into meaningful digital outputs through the use of sentiment analysis. Sentiment analysis, also known as opinion mining is the use of natural language processing, text analysis, computational linguistics to systematically identify, extract, quantify, and study affective states and subjective information expressed by a person towards a topic or a phenomenon. This project aims to use sentiment analysis to identify the various sentiments of a given text or news related to COVID-19 on social media platforms such as Facebook and Twitter. Various unsupervised machine learning algorithms, such as Vader(Valence Aware Dictionary for Sentiment Reasoning), Textblob and also pretrained BERT model on IMDB data are used to label messages by performing text classification. These classifiers will classify the text into three different sentiments positive, neutral and negative and will be compared against the sentiments that are manually labelled.