Abstract: Social media has played an important role in disaster emergency responses, which is increasingly being regarded as mobile sensors, perceiving events near human beings.When an emergency occurs, a large number of images and texts with geographic information quickly flood the social network. This paper presents a new method of mining and analysis of emergency information with a case study to analyze the Sina-Weibo text streams during and after the 2012 ‘Beijing Rainstorm’. The topic classification model of real-time emergency information is built, and the emergency information from real-time text stream are identified and located. Decomposition of seasonal components from the time series data is applied to explore the trend of the number of Sina-Weibo texts related to the ‘Beijing rainstorm’. According to different topics,using statistical and spatial analysis, a possible spatial structure for distributing resources in response to emergencies is indicated. The study can help to understand how the emergency events are evolved and what are impacted by the events, which will benefit decision-makers by allowing timely decisions emergencies for effective mitigation efforts and better allocation of resources.