Jakarta congestion mapping and classification from twitter data extraction using tokenization and na??ve bayes classifier

The data potential of Twitter is a powerful resource for data mining exploration. This research aims to pull the traffic information in Jakarta from Twitter. The first output is to develop a web application that can display Jakarta´s traffic situation in real time. The process include filtering and tokenizing to get the traffic jam´s location and direction to be displayed on Google Map. The second output is to develop a predictive analysis system to oversee Jakarta traffic pattern in a certain period of time using Naïve Bayes Classifier.