Title: Extended opinion lexicon and ML-based sentiment analysis of tweets: a novel approach towards accurate classifier

Authors: Gaurav Dubey; Santosh Kumar; Sunil Kumar; Pavas Navaney

Addresses: ABES Engineering College, Ghaziabad, India ' ABES Engineering College, Ghaziabad, India ' Amity University, Noida, India ' Amity University, Noida, India

Abstract: Micro-blogging, today has become a very trendy communication tool among internet users. Millions of users share their opinions on diverse aspects of life which are rich sources for opinion mining. This paper addresses the sentiment analysis of twitter data on demonetisation. A new approach to sentiment analysis based on extended opinion lexicon-based-scores is presented in this paper. Naïve Bayes algorithm and the simple voter algorithm has been used along with supervised learning algorithm like SVM, maximum entropy and GLMNET which are further compared. An insights of demonetisation, that include positive, negative and neutral classification of tweets, emotions of the people behind the tweet using the sentiment package in R has also been discussed. Experimental analysis shows that the extended opinion lexicon method performs better amongst all the supervised and non-supervised machine learning algorithms.

Keywords: micro-blogging; sentiment analysis; naïve Bayes algorithm; voter algorithm; opinion mining; lexicon; SVM.

DOI: 10.1504/IJCVR.2020.110640

International Journal of Computational Vision and Robotics, 2020 Vol.10 No.6, pp.505 - 521

Received: 05 Jan 2019
Accepted: 21 Jun 2019
Published online: 27 Oct 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article