SENTIMENT ANALYSIS OF INDONESIA'S CAPITAL CITY RELOCATION USING THREE ALGORITHMS: NAÏVE BAYES, KNN, AND RANDOM FOREST

Abstract

The relocation of Indonesia's capital city from Jakarta to the IKN Nusantara on the island of Borneo has become a trending topic that triggers conversations and opinions on various social media. The pros and cons of this policy are very pronounced in various media, especially on Twitter or X platform. The purpose of this research is to conduct a public sentiment analysis of public opinion related to the relocation of Indonesia's capital city. Data is taken from tweets comments collected during a certain period from June to September 2023. This research uses a Natural Language Processing approach with data pre-processing techniques to prepare the data before applying labeling and classification algorithms. This research tests the accuracy of three algorithms used in classification, namely Naïve Bayes Classifier, K-Nearest Neighbor, and Random Forest. The results of the data classification show that positive sentiment has a value of 36.8%, neutral sentiment is at 25%, and negative sentiment related to the relocation of the capital city is 38.1%. Then an accuracy test was carried out on the Naïve Bayes Classifier Algorithm method which found an accuracy value of 65.26%, the K-Nearest Neighbor Algorithm of 58.25%, and the Random Forest Algorithm of 45.05%. This shows that the Naïve Bayes Classifier Algorithm method has better accuracy than other algorithms in predicting classification in sentiment analysis. This research also identifies the frequency of key words that often appear in each sentiment which can be valuable information for monitoring public opinion on social media.