CineXDrama: Relevance Detection and Sentiment Analysis of Bangla YouTube Comments on Movie-Drama using Transformers: Insights from Interpretability Tool
This addresses the need for automated sentiment analysis in Bangla social media content, but it is incremental as it applies existing transformer methods to a new dataset.
The paper tackled the problem of filtering irrelevant comments and analyzing sentiment in Bangla YouTube comments on movies and dramas, achieving 83.99% accuracy for relevance detection and 93.3% for sentiment analysis using BanglaBERT.
In recent years, YouTube has become the leading platform for Bangla movies and dramas, where viewers express their opinions in comments that convey their sentiments about the content. However, not all comments are relevant for sentiment analysis, necessitating a filtering mechanism. We propose a system that first assesses the relevance of comments and then analyzes the sentiment of those deemed relevant. We introduce a dataset of 14,000 manually collected and preprocessed comments, annotated for relevance (relevant or irrelevant) and sentiment (positive or negative). Eight transformer models, including BanglaBERT, were used for classification tasks, with BanglaBERT achieving the highest accuracy (83.99% for relevance detection and 93.3% for sentiment analysis). The study also integrates LIME to interpret model decisions, enhancing transparency.