Volume 20 No 12 (2022)
 Download PDF
Sentiment Based Text Analysis on Social Media Brand Review Using Machine Learning
Kajal Mathur , Dr.Paresh Jain ,Dr.Sunita Gupta , Puneet Mathur
Abstract
Text Analysis requirements are increasing day by day due to expansion of application scope. Among them social media-based text is become popular in various human welfare task i.e., health care, disaster management and others. But automated accurate and reliable social media text analysis is a need of current applications. In this paper, we explored recent development on sentiment-based text analysis using social media data. Thus, first a review has been reported to identify popular area of application, feature selection techniques and classification methods. Then key issues in social media-based text analysis have been addressed. Further, a social media product review dataset has been considered for performing experimental study. The aim of this experimental study is to identify the suitable feature selection technique which is able to deal with the addressed issues. In addition, we involved some classical text classification approaches as well as deep learning technique to select the suitable technique of classification. According to our findings based on experiments the classical classifiers are less accurate in comparison with the deep learning-based techniques. In addition, the TF-IDF based features are more appropriate for classifying multiclass sentiment classification. However, the TF-IDF based features need some improvements to deal with the social media-based text analysis. Therefore, we also introduce the future extension plan.
Keywords
text analysis, text classification, text features, classifier, application, survey.
Copyright
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.