Dataset of Naïve Bayes-Based Data Analysis on Online Travel Agency’s Guest Review of Sheraton Bandung Hotel & Towers
Description
This dataset contains reviews of five-star hotel guests, namely Sheraton Bandung Hotel & Towers, collected from several Online Travel Agent (OTA) platforms: Traveloka, Tripadvisor, and Agoda. These reviews use Indonesian to express guests' opinions, such as service quality, hotel facilities, and comfort. By analyzing this review data, this study aims to determine the proportion of positive and negative reviews and identify the main aspects that consumers often mention. The results of this study can provide greater insight into the factors affecting guest experience and satisfaction in staying at a hotel. This dataset was collected by conducting effective web scraping using Octoparse. The data collected from the three OTA platforms were 1,367 reviews. Then, data cleaning was carried out from duplicate and irrelevant reviews, so the total data became 1,230 reviews. This study will classify the data into positive and negative sentiments using machine learning. In the initial observation, the reviews showed a mixture of feedback given. Many consumers felt that the hotel was good and comfortable, followed by complaints about the consistency of service quality and facilities. Each platform presents diverse reviews and shows variation in guest experience each time they visit, especially regarding the quality of service and in-room facilities. This dataset can be used by researchers conducting sentiment analysis studies, especially in the hospitality industry in Indonesia, to understand hotel guests' experiences and identify things that need to be maintained or improved. In addition, this dataset can serve as training data for machine learning models in sentiment classification. By understanding guest reviews, this dataset can be the basis for businesses to improve their reputation and provide strategic recommendations for developing the hospitality industry in Indonesia.