K-Nearest Neighbor and Naive Bayes Classifier Comparison for Individual Character Classification on Twitter

Abstract

Twitter is one of the most commonly used social media, especially in Indonesia. People use Twitter social media to express their opinions every day. This allows the DISC method to be applied to find out Twitter user's character. By knowing their characters using the DISC method and Twitter, this can help parties like the HRD without spending more effort in selecting employees. Three main processes are performed in this study, data acquisition, pre-processing, and calculation process. Classification methods, namely Text Naïve Bayes Classifier algorithm and K - Nearest Neighbor, are used to classified and mapping tweet data to the DISC method. As a result, the accuracy of the Naïve Bayes Classifier algorithm is 34.16%, while the K – Nearest Neighbor is 28.33%. So it can be concluded that the Naïve Bayes Classifier algorithm has a higher accuracy of 5.83% compared to K – Nearest Neighbor in classifying a Twitter account with TF-IDF Weighting into DISC method.