Sentiment Analysis E-commerce Review
Be Muhammad Doohan Abighail, Fachrifansyah, Muhammad Reyhan Firmanda, Maria Susan Anggreainy, Harvianto, Gintoro
Abstract
Reviews give customers the opportunity to tell the rest of the world about how they love or hate a product. While there is a limit to the number of words, there is no limit to the words that reviewers can use to express their anger, frustration, excitement or joy in buying the product. Online reviews have become such a standard part of the buying process for many people these days that every online retailer needs to think about optimizing them in their business strategy. The sheer number of reviews requires a special method or technique that can automatically categorize reviews, whether they are positive or negative. This research tries to classify e-commerce reviews with Naïve Bayes Classifier (NBC). The results of this research show that the accuracy with NBC is 72%, Recall 72% and Precision 78%.