<![CDATA[The hospitality industry relies heavily on customer satisfaction, which is often reflected through reviews on online travel applications. Hotel Zuri Express Lippo Cikarang requires an automated sentiment monitoring system to enhance its service quality. This study aims to implement the Naive Bayes Classifier algorithm to classify customer review sentiments into positive and negative categories. The research dataset consists of 1,637 reviews obtained via web scraping from the google maps. The research methodology includes text preprocessing, Term Frequency-Inverse Document Frequency (TF-IDF) weighting, and N-Gram (Bigram) feature modeling. The experimental results demonstrate that the model achieves an accuracy rate of 91.16%, with a precision of 0.91 and a recall of 0.99 for the majority class. Keyword analysis using Word clouds identified cleanliness and staff service as the primary factors driving customer satisfaction. Despite challenges in detecting negative sentiments within an imbalanced dataset, the Naive Bayes algorithm proved to be reliable and efficient for automated sentiment analysis, providing a robust tool to support fast and accurate management decision-making.Keywords: Sentiment Analysis; Customer Reviews; Hotel Zuri Express; Naive Bayes; Text mining.AbstrakIndustri perhotelan sangat bergantung pada kepuasan pelanggan yang tercermin melalui ulasan aplikasi travel online. Hotel Zuri Express Lippo Cikarang memerlukan sistem otomatis untuk memantau sentimen guna meningkatkan kualitas layanan. Penelitian ini bertujuan mengimplementasikan algoritma Naive Bayes Classifier dalam mengklasifikasikan sentimen ulasan pelanggan ke kategori positif dan negatif. Data penelitian mencakup 1.637 ulasan hasil web scraping dari google maps. Tahapan penelitian meliputi preprocessing teks, pembobotan kata Term Frequency-Inverse Document Frequency (TF-IDF), serta pemodelan fitur N-Gram (Bigram). Hasil pengujian menunjukkan model menghasilkan tingkat akurasi sebesar 91,16%, dengan nilai presisi 0,91 dan recall 0,99 pada kelas mayoritas. Analisis kata kunci melalui Word cloud mengidentifikasi aspek kebersihan dan pelayanan staf sebagai faktor utama kepuasan pelanggan. Meskipun terdapat tantangan dalam mendeteksi sentimen negatif pada dataset tidak seimbang, algoritma Naive Bayes terbukti handal dan efisien dalam melakukan analisis sentimen otomatis untuk mendukung pengambilan keputusan manajemen hotel secara cepat dan akurat.Kata kunci: Analisis Sentimen; Ulasan Pelanggan; Hotel Zuri Express; Naive Bayes; Text mining.]]>
Copyrights © 2026
