<![CDATA[Halal tourism has become an increasingly important sector due to the growing diversity of tourist preferences and the rapid development of digital platforms that generate large amounts of opinion data. However, sentiment classification in halal tourism remains challenging because tourist opinions often contain complex patterns and class imbalance. This study aims to improve the accuracy of halal tourism sentiment classification by applying a stacking ensemble approach based on machine learning algorithms. The proposed model combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost as base learners, while Logistic Regression is used as the meta-learner to integrate the prediction results of the base models. The research process includes data preprocessing, class balancing using Synthetic Minority Over-sampling Technique (SMOTE), and model validation using 5-Fold Cross-Validation. The evaluation was conducted using accuracy, precision, recall, F1-score, confusion matrix, and ROC curve. The experimental results show that the stacking ensemble model achieved an average accuracy of 80.55%, outperforming the individual base models, namely SVM with 79.77%, MNB with 79.27%, and AdaBoost with 70.77%. In addition, the stacking model obtained an AUC value of 0.8795, indicating strong discriminative ability in distinguishing sentiment classes. These results demonstrate that the stacking ensemble approach can improve classification performance and provide a more robust and reliable model for halal tourism sentiment analysis. Therefore, the proposed method can support data-driven decision-making in halal tourism management and promotion.]]>
