<![CDATA[The Ministry of Education and Culture (Kemendikbud) announced the Merdeka Belajar policy in early 2020 as an effort to reform the national education system. This policy has generated various responses from the public, including both support and criticism. Twitter, as one of the most widely used social media platforms, has become a primary medium for the public to express their opinions, feedback, and perspectives on this policy. Sentiment analysis can be utilized to identify and classify public opinions embedded in Twitter posts to understand societal responses toward the Merdeka Belajar policy. This study aims to develop a sentiment analysis model for the Merdeka Belajar policy using a Convolutional Neural Network (CNN) algorithm. The model is designed to classify sentiments into three categories: positive, negative, and neutral. Additionally, this study applies hyperparameter tuning to optimize the model’s performance in sentiment classification. Hyperparameter tuning is conducted to determine the best parameter combination to enhance the model's accuracy. The results indicate that the developed model achieves a sentiment classification accuracy of 82.54%.]]>
Copyrights © 2023
