COMPARISON NAÏVE BAYES CLASSIFIER, K-NEAREST NEIGHBOR AND SUPPORT VECTOR MACHINE IN THE CLASSIFICATION OF INDIVIDUAL ON TWITTER ACCOUNT

aristin chusnul khotimah (universitas amikom yogyakarta)
Ema Utami (Magister Teknik Informatika Universitas Amikom Yogyakarta)

Jurnal Teknik Informatika (JUTIF)
Vol. 3 No. 3 (2022): JUTIF Volume 3, Number 3, June 2022

In current’s digital era, people can take advantage of the ease and effectiveness of interacting with each other. The most popular online activity in Indonesia is the use of sosial media. Twitter is a social media that allows people to build communication between users and get the latest information or news. Information obtained from twitter can be processed to get the characteristics of a person using the DISC method, DISC is a behavioral model that helps every human being why someone does. To classify the tweet into the DISC method using algorithms naïve bayes classifier, k-nearest neighbor and support vector machine with the TF-IDF weighting. The results is compare the accuracy of the naïve bayes classifier algorithm has an accuracy rate of 31.5%, k-nearest neighbor has an accuracy rate of 23.8%, while the support vector machine has an accuracy rate of 28.4%.