City-Scale Social Event Detection and Evaluation with Taxi Traces

摘要: A social event is an occurrence that involves lots of people and accompanied by obvious rise in human flow. Analysis events has real-world importance because bring about impacts on many aspects city life. Traditionally, detection impact measurement rely investigation, which considerable effort. Recently, analyzing messages networks, researchers can also detect evaluate country-scale events. Nevertheless, the analysis city-scale not been explored. In this article, we use flow dynamics, reflect activeness a region, to measure their impacts. We first extract dynamics from taxi traces. Second, propose method only discover happening time venue abnormal activeness, but scale through changes such activeness. Third, traffic congestion information traces its change during impact. The results experiments validate effectiveness both methods.