<![CDATA[Berikut adalah paragraf yang sudah dirapikan: Traffic congestion in big cities in Indonesia is unavoidable, especially in Jakarta. The increasing number of vehicles and the lack of public transportation are the main causes of traffic congestion in Jakarta. It disturbs people's activities. The government has already made various efforts to resolve the congestion problem; however, it requires high installation and maintenance costs and takes time to be implemented. People often complain about traffic congestion in Jakarta by posting on Twitter, which are called tweets. Every tweet posted is saved in the Twitter API and used for sentiment analysis. It analyzes the emotions of the users. Based on these problems, we conducted research on how to detect traffic congestion in Jakarta. Therefore, we tried to create a Congestion Detection App. We designed the app using UML diagrams. The Congestion Detection App is connected with Hadoop, Flume, Hive, and Derby. The app streams Twitter data collected by connecting with the Twitter API. This app is a Java-based application that can create and view data tables. It performs searches on tweets by ID and analyzes traffic conditions in specific regions in Jakarta. The app performs sentiment analysis on certain tweets and displays the results based on the data tables. The result of the research compares data from the Congestion Detection App with data from Google Maps. We made three value categories consisting of three colors: green for less traffic congestion with a value of 1, orange for medium-scale traffic congestion with a value of 2, and red for heavy traffic congestion with a value of 3. Based on these three categories and values, we used four regions as samples and compared the values with those from Google Maps data to determine accuracy. We achieved an 81% average accuracy from the four samples. The data from the tweet samples compared with Google Maps data showed significant congestion detection with the Congestion Detection App.]]>
