Effect of Negation in Sentences on Sentiment Analysis and Polarity Detection

Sentiment analysis is one of the sub-domains of Natural Language Processing (NLP) that is of piqued interest in the research community. With the advent of e-commerce and social media, more and more customer opinions are being provided online in the written text form. Nowadays, sentiment analysis pro...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science 2021, Vol.185, p.370-379
Main Authors: Mukherjee, Partha, Badr, Youakim, Doppalapudi, Shreyesh, Srinivasan, Satish M., Sangwan, Raghvinder S., Sharma, Rahul
Format: Article
Language:English
Subjects:
Deep Learning
Machine Learning
Natural Language Processing Negation Identification
Sentiment Analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sentiment analysis is one of the sub-domains of Natural Language Processing (NLP) that is of piqued interest in the research community. With the advent of e-commerce and social media, more and more customer opinions are being provided online in the written text form. Nowadays, sentiment analysis provides a way for companies to understand customer opinions towards products and services in a global marketplace. Negative sentences or using negations in sentences have a significant impact on sentiment polarity detection. Inappropriate processing of negations in leads to biases and misclassification of sentiments. In this paper, we provide a novel end-to-end sentiment analysis approach to handle negations, along with the inclusion of negation identification and negation scope marking. Our approach introduces a customized negation marking algorithm for explicit negation detection and perform experiments on sentiment analysis with different machine learning algorithms such as Naïve Bayes, Support Vector Machines, Artificial Neural Network (ANN), and Recurrent Neural Network (RNN) on sentiment analysis of Amazon reviews, specifically of cell phones. By evaluating the effect of the negation algorithm on the sentiment analysis tasks, the RNN achieved the best accuracy of 95.67% when combined with our negation marking processing, exceeding its accuracy without any identification of negative sentences. Further, our approach was applied to another dataset of Amazon reviews and demonstrated a significant improvement in the overall accuracy.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2021.05.038