<![CDATA[Shopee is one of the most popular online marketplaces in Indonesia, with more than 103 million users in 2023. Most users consider factors such as customer reviews, ratings, prices, and free shipping promotions before making a purchase. Analyzing user reviews is essential to understand consumer perceptions of services, identify satisfaction or dissatisfaction, and detect potential issues that need to be addressed. However, sentiment analysis faces challenges in processing text with diverse language styles, structures, and informal expressions. To overcome these challenges, this study applies machine learning algorithms—Support Vector Machine (SVM) and K-Nearest Neighbors (KNN)—for classifying sentiment in Shopee user reviews. Data labeling using the Lexicon InSet method produced 9,509 positive reviews (47.55%), 7,686 negative reviews (38.43%), and 2,805 neutral reviews (14.03%). Based on the Confusion Matrix results, SVM outperformed KNN, particularly in classifying negative and neutral sentiments with higher accuracy. These findings indicate that SVM is a more effective and efficient model for sentiment analysis of user reviews on the Shopee platform.]]>
Copyrights © 2024
