Sentiment Analysis of YouTube Comments Using Machine Learning Algorithm

The extensive user engagement on YouTube leads to a flood of comments, creating challenges for content creators who aim to understand audience sentiment. Previous studies have mainly concentrated on distinguishing between positive, negative, and neutral sentiments in comments. This study involves creating a dataset of YouTube comments and classifying them into positive, negative, interrogative, corrective, imperative, and neutral categories, which will help content creators visualize other sentiments alongside positive, negative, and neutral sentiments. Based on the sentiment, they can improve their content and also enhance user interaction. Six machine learning algorithms—Naive Bayes (NB), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)—are applied, with the SVM model demonstrating outstanding accuracy, reaching 94%.