Analisis Sentimen Terhadap Ulasan Pengguna Pada Aplikasi Traveloka Menggunakan Metode Naïve

The proliferation of user-generated reviews on digital platforms provides in-depth information to improve services. The purpose of this study is to apply the Naïve Bayes approach to analyze the sentiment of user evaluations of the Traveloka application sourced from the Google Play Store. Through online search, 10,000 evaluations were collected. Case folding, stopword elimination, tokenizing, and stemming are some of the pre-processing techniques used. Based on the review scores, the sentiment data was classified into two groups: positive and negative. Furthermore, the Naïve Bayes model was used for classification, and a confusion matrix was used to assess the results. The results showed an accuracy of 89.35%, precision of 88.44%, recall of 95.05%, and F1-Score of 91.62%. These results demonstrate the effectiveness of the Naïve Bayes approach in categorizing user reviews, providing Traveloka with important information about customer perceptions and how to improve their service quality. The findings from this study are expected to be the basis for future advancements in sentiment analysis on travel and accommodation-related applications.