PERBANDINGAN KINERJA NAÏVE BAYES DAN SVM PADA ANALISIS SENTIMEN TWITTER IBUKOTA NUSANTARA

Abstract

The national capital is the center of government of a country and is often a symbol of sovereignty and national identity. The function and role of the capital city is very important in coordinating government activities, public policies and community services. This research aims to compare the effectiveness of two approaches for classification: Support Vector Machine and Naïve Bayes (SVM), in analyzing opinion sentiment towards the Indonesian capital based on Twitter data. Opinion sentiment analysis is crucial for understanding public views regarding various aspects of the Indonesian capital. The Twitter data used will involve opinions developing on social media regarding the Indonesian capital. The research methodology involves data collection, preprocessing, data sharing, Naïve Bayes and SVM model training, evaluation, and statistical analysis to compare the performance of the two models. Naïve Bayes and Support Vector Machine are the approaches employed in this study. The research results from the Naïve Bayes method present a sentiment analysis accuracy rate of 91%. The SVM method also provides a sentiment analysis accuracy rate of 94%. In light of the analysis's findings, the procedure utilizing the Support Vector Machine (SVM) method shows better results than the Naïve Bayes method in measuring sentiment towards the Indonesian capital.