<![CDATA[The increase in Value Added Tax (VAT) as part of the government's fiscal policy has caused various responses from the public. This study aims to determine public perceptions of the VAT increase policy by analyzing sentiments expressed through Twitter social media. A total of 1500 Indonesian-language tweets were collected using Tweet-Harvest in the period from June 1, 2024 to June 1, 2025. The data was then processed through the stages of cleaning, case folding, tokenizing, stopword removal, and stemming. Text features were extracted using the Term Frequency-Inverse Document Frequency (TF-IDF) method, and classified into positive, negative, and neutral sentiments using the Support Vector Machine (SVM) algorithm with a linear kernel. The classification results showed that neutral sentiment was the most dominant, followed by negative and positive sentiments. The SVM model performed well with an accuracy of 89.09%, proving its effectiveness in classifying Indonesian-language social media texts. This study is expected to provide input for the government in understanding public perception of the policies implemented, as well as demonstrating the potential of sentiment analysis as a tool in digital public opinion-based decision making.]]>
Copyrights © 2025
