A Real Time Event Detection using Probabilistic Method and Analysing through Twitter

A probabilistic model provides a way to detect multiple instances of real time events and to estimate the location of targeted event like earthquakes, typhoons, traffic jams. For this, two models have been proposed named temporal and spatial models to detect real time events and estimate the targeted event locations respectively by dealing with sensor reading appropriately. Our work is based on the twitter-which is used to deal with sensor reading appropriately real time events and particularly for location estimation. An important characteristic of twitter is its real-time nature. We investigate the real-time interaction of events such as earthquakes in twitter and propose an algorithm to monitor tweets and to detect a target event. As an application, we develop an earthquake reporting system for use in Japan. Because of the numerous earthquakes and the large number of Twitter users throughout the country, we can detect an earthquake with high probability (93 percent of earthquakes of Japan Meteorological Agency (JMA) seismic intensity scale 3 or more are detected) merely by monitoring tweets. Our system detects earthquakes promptly and notification is delivered much faster than JMA broadcast announcements.