<![CDATA[Public service institutions face constant expectations to provide excellent service to participants and minimize complaints. With advances in technology, participants can now provide direct feedback on public services via online platforms, such as Google Reviews. This study aims to analyze participants’ sentiment toward the services of the BPJS Kesehatan Kupang Branch using a quantitative approach. The data collection process employed Python web scraping to retrieve 530 reviews through March 2025. The collected text underwent comprehensive preprocessing, including cleaning, tokenization, stopword removal, and stemming, to ensure data . We assigned sentiment labels based on star ratings: 4- and 5-star reviews were classified as positive, 1- and 2-star reviews as negative, and 3-star reviews were excluded as neutral. A final dataset of 529 reviews was then processed using the Naïve Bayes classifier. The results show that the Naïve Bayes algorithm successfully classified sentiments with an accuracy rate of 98.11%. Additionally, the analysis revealed that positive sentiment accounted for 98.3%, driven by keywords related to service speed and staff friendliness. These findings indicate that sentiment analysis of online reviews is an effective and objective tool for evaluating participants’ perceptions of public service quality.]]>
Copyrights © 2025
