Twitter sentimental analysis on fan engagement

Abstract

Sentimental analysis involves determination of opinions, feelings, and subjectivity of text. Twitter is a social networking service where millions of people share their thoughts. Twitter sentimental analysis on fan engagement focuses on how fans in different sports industry actively engage on social media. Fans are identified based on their opinions and emotions expressed in the tweet. In this paper, we provide a comparative analysis of machine learning algorithms such as multinomialNB, support vector machine, linearSVM, and decision trees. The traditional approach involves manually assigning labels to training data which is time-consuming. To overcome this problem, we use TextBlob which computes the sentiment polarity based on POS tagging and assigns sentiment score to every tweet in range of −1 to +1. We compute the subjectivity of text which is in the range of 1–0. We also identify the sarcastic tweets and assign correct class labels based on the weightage we provide for every word. Our experimental result shows how accuracy gets increased with the use of advanced machine learning algorithms.