Real-Time Traffic Congestion Analysis Based on Collected Tweets

Due to the rapid increase in the use of and advancement of social media platforms, the amount of data available on the internet is increasing. The available information on the internet can be used to gain insights about searching trends and public interests. The advancements in machine learning and deep learning techniques drastically improved data analytics and processing solutions for social media and infotainment industry. It is no doubt that the majority of regular commuter encounters traffic congestion daily. There is a growing number of population in Metropolitans. This leads to higher population density rates and traditional methods for collecting traffic information using physical sensors are expensive, however, by using social media tools information regarding traffic jam, road and traffic congestion can be improved. In this paper, we analyze traffic congestion using Twitter data (tweets) in real-time. The proposed model extracts traffic-related tweets from Twitter and classifies the extracted information for traffic commute estimation road. In this study, tweets from Los Angeles, USA are taken into consideration as an analysis example. A machine learning classifier and a deep learning classier are used to classify traffic information. The model was trained to collect tweets containing the word 'traffic' in a real-time environment.