<![CDATA[Improving the quality of Public Services is a major need in the era of digitalization, including in the local taxation sector related to the sentiment of services provided in tax payments. The purpose of this study was to analyze public sentiment towards tax payment services in the Office of the regional Revenue Agency (Bapenda) Labuhanbatu Utara by applying Naïve Bayes algorithm using Rapid Miner software. Data analysis through text preprocessing, feature selection, and sentiment classification into positive, negative, and neutral categories. The Data obtained consisted of 225 community comments from the SIMPATDA application and 612 tweets with the hashtag #pajakLabura from Twitter, which reflected people's opinions directly. The analysis process is carried out through the stages of text preprocessing, feature selection, to the classification of sentiments into positive, negative, and neutral categories. The results showed that the Naïve Bayes algorithm is able to classify public opinion with a high degree of accuracy and establish similarities/differences in the aspects of service that are most complained about or appreciated by the public. This study also contributes to the development of data-based evaluation system in the scope of public services.]]>
Copyrights © 2025
