<![CDATA[In the rapidly growing world of e-commerce, customer reviews play a crucial role in influencing purchasing decisions. However, the massive volume of online reviews makes it difficult for potential buyers and sellers to interpret the overall sentiment toward a product. This research aims to perform sentiment analysis on product reviews in e-commerce platforms using the Naive Bayes classification method. The study focuses on classifying reviews into positive, negative, and neutral categories based on textual data. The dataset used consists of customer reviews collected from popular e-commerce sites. The data preprocessing stages include case folding, tokenization, stop word removal, and stemming to ensure clean and meaningful input for the model. The Naive Bayes algorithm, known for its simplicity and efficiency in text classification, is applied to train and predict sentiment labels. Evaluation is conducted using accuracy, precision, recall, and F1-score metrics to measure model performance. Experimental results show that the Naive Bayes classifier achieves high accuracy in detecting sentiment polarity, making it suitable for large-scale sentiment analysis in e-commerce contexts. The findings demonstrate that sentiment analysis can provide valuable insights for businesses in understanding customer satisfaction, improving products, and enhancing overall marketing strategies. ]]>
Copyrights © 2025
