Classification of Traffic Congestion in Indonesia Using the Naive Bayes Classification Method

Abstract

The purpose of this research is to analyze the accuracy of congestion data using Google Colab in detecting congestion by the province in Indonesia the author tries to test strategies for dealing with congestion in the Indonesian region by utilizing the Naïve Bayes method. In this journal, apply with Google Collab . This research uses data that comes from crawling data on Twitter. Using the Naive Bayes method to find the shortest route is efficient and not congested. Implementation of online school transportation using the naive Bayes method in minimizing travel costs to pick up students can reduce traffic jams, reduce accidents, reduce student tardiness, and minimize travel costs. The Naive Bayes method can be used to identify relevant information about traffic jams in Indonesia through Twitter data with a good degree of accuracy. These results can assist decision-making and strategic planning in overcoming the problem of traffic congestion in Indonesia. Therefore, this research implies that it can help improve the accuracy of traffic congestion data in Indonesia. By using Google Colab, more advanced analysis methods and machine learning algorithms can be applied to process the existing traffic data. Additionally, utilizing Google Colab allows for fast and efficient data processing.