Application of The Naive Bayes Classifier Method In The Sentiment Analysis of Twitter User About The Capital City Relocation


  • Syafa’at Adi Nugraha UIN Sunan Kalijaga
  • Maria Ulfah Siregar UIN Sunan Kalijaga


capital city, movement, naive bayes, TF-IDF, split validation, confusion matrix


The president's official decision regarding the relocation of the capital city, which previously was in Jakarta and will be moved to East Kalimantan, will be a big issue and generate a lot of debate from both the agree and the disagree Indonesian citizen because this project will require a lot of funds and will have massive impacts on various sectors. This study uses 1290 tweet data consisting of 686 negative sentiments and 603 positive sentiments. These data were used as training data to create evaluation models using confusion matrix and split validation techniques. In this study, it is used TF-IDF word-weighted feature extraction with the Naive Bayes method. The result from the experiments, which was carried out on the best accuracy by splitting data 90:10 for training and testing respectively, is 76.74%. The model that has been made is implemented in 1115 test data resulting in 799 negative sentiments and 316 positive sentiments.

Author Biographies

Syafa’at Adi Nugraha, UIN Sunan Kalijaga

Informatics Department

Maria Ulfah Siregar, UIN Sunan Kalijaga

Informatics Department Magister Program