Analisis Sentimen Terhadap Pemerintahan Ridwan Kamil Sebagai Gubernur Jawa Barat Menggunakan Algoritma Naïve Bayes

Abstract

The use of social media in the era of globalization is very necessary for some circles including the regional leader, in the period of his tenure, Ridwan Kamil received various inputs and criticisms, and in this case the authors conducted research to analyze public sentiments towards the elected governor. And in this study the authors use the Naïve Bayes algorithm to classify sentiments and look for the preference values because the algorithm has a pretty good accuracy. From the results of tests conducted using cross validation techniques and accuracy measurements using confusion matrix with 10 times the best accuracy testing obtained was 84.38% and the positive response obtained from the calculation of preference value was 49%. Thus it can be concluded that the Naïve Bayes algorithm can be used to classify quite well and be able to measure the community's response to regional leaders.

Keywords: Sentiment Analysis, Twitter, Naïve Bayes Classifier, Cross Validation, Preference Value