Sentiment Analysis on The Shopee Platform Using The Naive Bayes Algorithm

Abstract

Shopee is one of the e-commerce applications with the largest user base in Indonesia. The increase in the number of users is directly proportional to the number of reviews left on the Google Play Store , so these reviews can be used as an important source of information regarding user experience and satisfaction levels. This study was conducted to analyze the sentiment of these reviews using the Naïve Bayes algorithm . There are three main focuses of the study, namely: (1) explaining the pre-processing stages of review text data, (2) testing the performance of the Naïve Bayes algorithm in classifying sentiments into positive, negative, and neutral, and (3) interpreting the classification results to provide an overview of user perceptions and satisfaction with the Shopee application. The research data was collected using web scraping techniques on 4,500 reviews of the Shopee app on the Google Play Store . with ratio of 70% as training data and 30% as test data. Stages pre-processing. covering cleaning, case folding, tokenizing, stopword removal, normalization as well as stemming. Next, the data is labeled according to sentiment categories and then processed using the Naïve Bayes algorithm . Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Test results show that the Naïve Bayes algorithm is capable of providing sentiment classification with a good level of accuracy. The majority of user reviews are positive, reflecting a high level of satisfaction with the Shopee app. This research is expected to provide input for app developers and e-commerce businesses in designing service improvement strategies based on user perceptions.