| dc.description.abstract | This study focuses on analyzing YouTube comments to determine their sentiment polarity—positive or negative—using machine learning algorithms. Four classifiers, namely Naive Bayes, Logistic Regression, Passive Aggressive Classifier, and Support Vector Machine (SVM), are implemented and compared to evaluate their performance. The study provides a detailed explanation of the preprocessing steps, feature extraction techniques, and algorithmic implementations. The results highlight the strengths and weaknesses of each classifier and offer insights for future research in sentiment analysis. Additionally, exploratory data analysis and the impact of feature engineering on model performance are discussed in detail. | en_US |
