TEXT MINING IN ONLINE TRANSPORTATION USER SENTIMENT ANALYSIS ON SOCIAL MEDIA TWITTER USING THE MULTINOMIAL NAIVE BAYESIAN CLASSIFIER METHOD AND K-NEAREST NEIGHBOOR METHOD

Abstract

Text mining is the process of detecting information or something new and researching large information. Text mining can also usually perform an analysis of unstructured text. Social media users in Indonesia, which currently almost reach 200 million users, have resulted in a flood of data. This condition makes text mining a solution to extract knowledge from the flood of data [1] . In exploring knowledge, there are various techniques or methods that can be adopted including the Multinomial Naive Bayesian Clasifier and K-Nearest Neighbor methods. Both of these methods have several phases that are able to explore the potential knowledge of a flood of supervised and unsupervised learning data. It is hoped that the combination of these two methods will help analyze public sentiment or perception towards online motorcycle taxi users in Indonesia