Twitter Sentiment Analysis using Machine Learning Algorithms: A Comparative Analysis

Abstract

Data posted by people, or the users of a particular social network, has increased dramatically due to the changing behavior of various social networking sites like Instagram, Twitter, Snapchat, etc. Innumerable millions and billions of bytes of audio, video, and text are uploaded daily. This is because millions of people use a particular website. These folks are interested in sharing their thoughts and opinions on any topic they choose. People also want to know if most people will see an incident favorably, unfavorably, or neutrally. In this paper, the data is classified into Positive, Negative, or Neutral opinions, and it presents a detailed survey of Sentiment analysis of Twitter data using various Machine learning algorithms like Naïve Bayes, Support Vector Machine (SVM), Logistic regression, and decision tree. Additionally, the accuracy and F1 scores of the aforementioned algorithms are examined on two distinct Twitter datasets, and a comparison is made between the algorithms respective accuracies in the two datasets