Sentiment analysis is a method for classifying text using a Natural Language Processing (NLP) machine learning approach. Sentiment analysis can be utilized in various sectors to help obtain information on customer satisfaction based on positive and negative categories. This study aims to conduct sentiment analysis on customer satisfaction based on product quality, goods delivery service, and seller response in a popular e-commerce application in Indonesia, Tokopedia. This research uses a dataset containing 29 product categories on Tokopedia. Modeling of this dataset will be analyzed using the Naïve Bayes approach and other data processing processes. Based on the analysis process, the researcher found that there were 52.9% negative reviews and the Naïve Bayes approach had good performance for negative sentiment and good precision of 0.99. However, this approach still has shortcomings in terms of generating recall and F1-Score for negative sentiment while positive sentiment shows a balanced performance.