The Classification of YouTube Bangla Comments Using Sentiment Analysis

Abstract

In this paper, the authors present a machine learning-based approach for sentiment analysis of Bangla language comments on YouTube. They propose an algorithm to classify comments as positive or negative and build models to extract the emotion of the comments. They evaluate the performance of the model using a new dataset of Bangla comments from various YouTube videos. They compare the performance of different algorithms such as Multinomial Naive Bayes (MNB), Stochastic Gradient Descent (SGD), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), AdaBoost, and XGBoost. The results show that MNB achieves the best accuracy of 70.88%. The paper suggests that there is a need for more research in the field of sentiment analysis of Bangla language.