Real-Time Detection and Visualization of Traffic Conditions by Mining Twitter Data

There have been various attempts to leverage the massive amount of data generated from social media websites. The real-time nature of social media platforms can help detect events, especially in a metropolitan city. In this paper, a system is proposed, that detects traffic-related events and road conditions in real-time from tweets by using classification algorithms and custom-trained named entity recognition model (NER) to classify and extract contextual information and visualise it on a map to get an overall picture of the traffic conditions in a city. The proposed system is versatile and can be applied to other use cases such as detecting calamities, social unrest, etc.