Comparison of Machine Learning Techniques on Twitter Emotions Classification

EasyChair Preprint 5518

Abstract

Social media has become an essential part of our social life nowadays. A huge amount of user reviews and comments shared by users on social media. Twitter has an excellent growth in social media and also known as a platform for business and news. Text classification is an important part of text mining in recent years. Emotion mining is the science of detecting, analyzing, and evaluating humans’ feelings towards different events, issues, services, or any other interest. This paper discusses the Twitter text classification using various machine learning algorithms based on the emotions such as love, anger, anticipation, disgust, fear, joy, optimism, pessimism, sadness, surprise, trust, and neural. The performance of the classifiers Random Forest, Logistic Regression, and Stochastic Gradient Boost are analyzed and the results are compared.

Keyphrases: Natural Language Processing, Random Forest, Stochastic Gradient Descent Boost, Twitter, emotions classification, logistic regression, machine learning, text classification, twitter emotion classification

@booklet{EasyChair:5518,
  author    = {S Santhosh Baboo and M Amirthapriya},
  title     = {Comparison of Machine Learning Techniques on Twitter Emotions Classification},
  howpublished = {EasyChair Preprint 5518},
  year      = {EasyChair, 2021}}