


Volume 20 No 20 (2022)
Download PDF
DEVELOPMENT OF AN IMPROVED TECHNIQUE FOR SENTIMENT ANALYSIS USING MACHINE LEARNING
Harshdeep Singh, Kanwal Preet Singh Attwal ,Madan Lal
Abstract
Sentiment Analysis is an application that concentrates on the identification and classification of ideas
indicated mainly in the form of positive, negative and neutral values. One of the most important
parts of machine learning is Feature Extraction and Selection. This paper revolves around Term
Frequency Inverse Document Frequency (TF-IDF) as Feature Extraction and Chi-Square (Chi) as a
Feature Selection technique to generate feature vocabulary and then use it with a Hybrid Tree to
bring out better results than by using machine learning algorithms. We compared the performance
of Feature Selection trained using Hybrid Tree (HT) against K-Nearest Neighbor (KNN), Support
Vector Machines (SVM), KNN+SVM, Sequential Minimal Optimization (SMO), Decision Tree (DT) and
SMO+DT. Our proposed work with TFIDF+HT is far more accurate as compared to other ML
algorithms.
Keywords
– Feature Selection, TF-IDF, Chi-Square, Sentiment Analysis, Machine Learning
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.