<![CDATA[Online reviews on platforms like TripAdvisor play a crucial role in consumer decision making and hotel reputation management. However, the massive and unstructured volume of data requires a fast and accurate automated analysis method. This study aims to analyze the sentiment of TripAdvisor hotel reviews and compare the performance of the Support Vector Machine (SVM) and Logistic Regression (LR) algorithms. The dataset consists of 20,491 reviews classified into three sentiment classes: positive, negative, and neutral. Feature extraction was performed using the Term Frequency-Inverse Document Frequency (TF-IDF) method. To handle the class imbalance issue and ensure robust evaluation, the models were evaluated using Stratified 10-Fold Cross-Validation. The results indicate that Logistic Regression outperforms Support Vector Machine, achieving an average accuracy of 81.46% and an F1-Score of 83.02%, compared to Support Vector Machine which obtained an accuracy of 80.41% and an F1-Score of 82.20%. Both models showed excellent performance on the positive class but faced challenges on the neutral class due to semantic ambiguity and majority class dominance. In conclusion, Logistic Regression proves to be a more optimal, stable, and efficient model for sentiment classification on imbalanced data, making it highly applicable for assisting hotel management in monitoring customer feedback in real time.]]>
Copyrights © 2026
