Casting online votes: To predict offline results using sentiment analysis by machine learning classifiers
P. Juneja, Uma Ojha · 2017
In today's world, Social Networking website like Twitter, Facebook, Instagram, etc. plays a very significant role. Twitter is a social networking website which provides loads of data that can be used for various purposes such as Sentiment Analysis for predictions, marketing, elections, etc. The objective of this research is to classify twitter data into sentiments (positive or negative) by using different supervised machine learning classifiers to predict the Delhi Corporation Elections results and to identify the most accurate machine learning classifier. The research highlights the performance of different classifiers on the twitter dataset related to political parties. Experiments show that Multinomial Naïve Bayes classifier is the most accurate sentiment predictors with 78%.