ARCHIVES
VOL. 9, ISSUE 3 (2023)
Sentiment analysis on Bengali comments to predict emotions
Authors
Papia Akter, Rabeya Sultana
Abstract
Sentiment Analysis, as
the term implies, is the process of determining the point of view or sentiment
underlying a scenario. It simply involves analyzing and determining the emotion
or intent behind a piece of writing, speech, or any other form of communication.
Sentiment analysis is one of the fastest-developing areas of computer
science research nowadays. Using sentiment analysis, a text may be separated
into several different emotions. Because there have been few studies on emotion
analysis in the Bangali language, it is recognized as an essential study
subject in Bengali language analysis. This study addresses three types of
emotions: negative, positive, and neutral. In this paper, we trained the
dataset using various machine learning techniques and obtained accuracy of
70.87% and 73.95% for Linear and RBF Support Vector Machine (SVM), 74.60% for
Logistic Regression (LR), 62.46% for Decision Tree (DT), 69.90% for Random
Forest (RF), 75.40% for Naive Bayes (MNB), and 67.48% for K-Nearest Neighbors
(KNN).
Download
Pages:15-23
How to cite this article:
Papia Akter, Rabeya Sultana "Sentiment analysis on Bengali comments to predict emotions". International Journal of Research in Advanced Engineering and Technology, Vol 9, Issue 3, 2023, Pages 15-23
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.