Sentiment Analysis of Hotel Reviews in Anyer Beach Tourism Area: A Lexicon-Based Text Mining Approach

Abstract

This study aims to analyze tourist sentiment towards hotels in the Anyer beach tourism area through online reviews. Sentiments and emotions expressed in these reviews were analyzed using a lexicon-based approach from the National Research Council (NRC) lexicon, which includes emotion categories such as anger, fear, sadness, joy, and disgust. Hotel review data were collected from TripAdvisor, and the analysis involved text preprocessing steps such as cleaning, case folding, stemming, and stopword removal. The sentiment analysis results reveal that most tourists provided positive reviews, with only 14.06% of the reviews displaying negative sentiment. Word cloud visualization identified the words "bad" and "dirty" as frequently appearing in negative reviews, likely pointing to cleanliness and service quality issues as the primary reasons for dissatisfaction. Emotional analysis showed dominant feelings of sadness, anger, disgust, and fear, likely triggered by unmet expectations regarding cleanliness and comfort during their stay. Based on these findings, it is recommended that hotel management in the Anyer beach tourism area address these concerns by implementing regular cleaning routines and staff training to enhance hotel service quality.