Clustering of User Reviews Using K-Means: A Case Study of Shopee Marketplace

An accurate understanding of user sentiment is essential for e-commerce companies in the rapidly growing online commerce era. Shopee, one of the largest e-commerce companies in Indonesia, has not yet been extensively analyzed for user sentiment using the K-Means method. The K-Means method is an easy and fast method for data clustering. It can also be used for large amounts of data so that it can be applied to predict Shopee Application User Review Sentiment. This research aims to apply the K-Means clustering method in sentiment analysis of Shopee application user reviews. This study successfully applied the K-Means clustering method to analyze the sentiment of Shopee application user reviews. The clustering results show the formation of three groups of reviews with different characteristics. Although the prediction accuracy did not reach a very high level, the evaluation and validation steps performed gave confidence in the quality of the clusterization obtained. This research provides initial insights into user perceptions of the Shopee application, and recommendations for future research include parameter tuning and dataset enhancement to improve prediction accuracy.