
With the rise of heterogeneous information delivering platform, the process of collecting, integrating, and analyzing disaster related information from diverse channels becomes more difficult and challenging. Further, information from multiple sources brings up new challenges for information presentation. In this paper, we design and implement a Disaster Situation Reporting System (Disaster SitRep) that is essentially a disaster information collecting, integration, and presentation platform to address three critical tasks that can facilitate information acquisition, integration and presentation by utilizing domain knowledge as well as public and private web resources for major disaster recovery planning and management. Our proposed techniques create a disaster domain-specific search engine and a geographical information presentation and navigation platform using advanced data mining and information retrieval techniques for disaster preparedness and recovery that helps impacted communities better understand the current disaster situation. Specifically, hierarchical clustering with constraints are used to automatically update existing disaster concept hierarchy; taxonomy-based focused crawling component is developed to automatically detect, parse and filter those relevant web resources; a domain-oriented skeleton for each type of disasters is used to extract disaster events from disaster documents by defining the set of structural attributes. Furthermore, the platform can perform not only as a domain-specific search engine but also as an information monitoring and analysis tool for decision support during recovery phase of disasters.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 6 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
