<![CDATA[This study investigates the role of sentiment analysis in improving service quality and guest satisfaction in the hospitality industry. Recognizing the increasing importance of customer feedback in shaping operational strategies, the research utilized a dataset of 1,141 original hotel reviews, comprising 1,113 positive and 28 negative sentiments. The methodology employed IndoBERT for sentiment classification, supported by a series of preprocessing steps, including text normalization, stopword removal, and text length filtering, to ensure data integrity. To address the significant class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, resulting in a balanced dataset of 1,923 reviews, with 1,450 positive and 473 negative sentiments. The model demonstrated strong performance, achieving an Area Under the Curve (AUC) score of 94.7%, highlighting its capability to classify sentiments accurately. Findings reveal that positive sentiments often focus on room quality, staff friendliness, and breakfast service, while negative feedback highlights service delays and cleanliness issues. These insights enable data-driven recommendations for improving guest experiences and addressing critical concerns. The study demonstrates the potential of sentiment analysis as a strategic tool for enhancing service delivery, fostering guest loyalty, and maintaining competitiveness in the hospitality market.]]>
Copyrights © 2025
