A New Two-layer Storyline Generation Framework for Disaster Management.

Disasters, such as hurricanes, earthquakes and environmental emergencies, are serious disruptions of the functioning of a community or a society. To mitigate the social and physical impact of disasters, a critical task in disaster management is to extract situation updates on the disaster from a large number of disaster-related documents, and obtain a big picture of the disaster's trends and how it affects different areas. In this paper, we present a novel two-layer storyline generation framework which generates an overall storyline of the disaster events in the first layer, and provides condensed information about specific regions affected by the disaster (i.e., a location-specific storyline) in the second layer. To generate the overall storyline of a disaster, we consider both temporal and spatial factors, which are encoded using integer linear programming. While for location-specific sto- rylines, we employ a Steiner tree based method. Compared with the previous work of storyline generation, which generates at storylines without considering spatial information, our framework is more suitable for large-scale disaster events. We further demonstrate the efficacy of our proposed framework through the evaluation on the datasets of three major hurricane disasters. [ABSTRACT FROM AUTHOR]