<![CDATA[Online reviews are widely used as a data source for evaluating hotel service quality because they reflect visitors’ experiences through ratings and textual feedback. Google Maps provides publicly accessible reviews that enable the analysis of visitor satisfaction toward hotel services. This study analyzes visitor satisfaction based on Google Maps reviews using machine learning–based classification methods within a case study framework. Review data were collected through web scraping and processed through data cleaning to remove duplicate, empty, and irrelevant entries. The cleaned reviews were transformed into numerical representations using the Term Frequency–Inverse Document Frequency (TF-IDF) method. Classification was performed using Logistic Regression and Support Vector Machine. Model performance was evaluated using an 80:20 training–testing split and standard metrics, including accuracy, precision, recall, and F1-score. The results indicate that Support Vector Machine achieves higher overall accuracy compared to Logistic Regression under the applied experimental conditions. However, Logistic Regression demonstrates more balanced performance across evaluation metrics, while Support Vector Machine tends to be more biased toward the majority class in identifying visitor satisfaction categories. These findings suggest that simpler linear models can still perform consistently in high-dimensional textual data, particularly in handling imbalanced review distributions. Furthermore, the analysis shows that classification results can be utilized to identify recurring patterns in visitor feedback, supporting a more systematic and data-driven evaluation of hotel service quality.]]>
