Crowd Sensing of Urban Emergency Events Based on Social Media Big Data

Detection about urban emergency events, e.g., The fires, storms, traffic jams is of great importance to protect the security of humans. While there are limited physical sensors such as surveillance cameras in a city, urban emergency events are still difficult to be detected for their real-time feature. Recently, social media feeds are rapidly emerging as a novel platform for providing and dissemination of information that is often geographic. The content from social media often includes references to urban emergency events occurring at, or affecting specific locations. In this paper, the real-time detection of urban emergency events based on social media is proposed. Firstly, users of social media are set as the target of crowd sensing. Secondly, the spatial and temporal information from the social media are extracted to detect the real-time event. Thirdly, a GIS based annotation of the detected urban emergency event is shown. The proposed method is evaluated with extensive experiments based on five real urban emergency events. The result show the accuracy and efficiency of the proposed method.