The rapid advancement of digital technology has significantly transformed the tourism industry, particularly in online hotel booking services such as Agoda. The large volume of user reviews available on this platform serves as a valuable data source for analyzing customer satisfaction and perceptions. This study aims to conduct sentiment analysis on 5,000 Indonesian-language user reviews from the Agoda mobile application by comparing the performance of three machine learning algorithms: K-Nearest Neighbors (KNN), Naïve Bayes, and Support Vector Machine (SVM). Data were collected using a web scraping technique from Google Play Store and processed through several preprocessing stages, including cleaning, case folding, tokenization, word normalization, stopword removal, and stemming. Text representation was performed using the CountVectorizer method, with an 80:20 ratio of training and testing datasets. The experimental results show that the SVM algorithm achieved the highest performance with an accuracy of 84.1%, outperforming Naïve Bayes (65.3%) and KNN (61.7%). These findings indicate that SVM demonstrates superior capability in classifying positive, negative, and neutral sentiments in Indonesian text. The results of this research are expected to contribute to the development of sentiment analysis models and support service quality improvement based on user feedback.