SAT: Spatial Awareness from Textual Input

Recent events (WTC attacks, Southeast Asia Tsunamis, Hurricane Katrina, London bombings) have illustrated the need for accurate and timely situational awareness tools in emergency response. Developing effective situational awareness (SA) systems has the potential to radically improve decision support in crises by improving the accuracy and reliability of the information available to the decisionmakers. In an evolving crisis, raw situational information comes from a variety of sources in the form of situational reports, live radio transcripts, sensor data, video streams. Much of the data resides (or can be converted) in the form of free text, from which events of interest are extracted. Spatial or location information is one of the fundamental attributes of the events, and is useful for a variety of situational awareness (SA) tasks. This demonstration will illustrate our approach, techniques and solutions for obtaining spatial awareness from raw input text. There are several challenges that arise in obtaining spatial awareness from raw text input modeling/ representation, event extraction and disambiguation, querying, reasoning and visualization. We specifically focus on illustrating solutions for (a)modeling and representation that captures spatial uncertainty in text and (b) efficient indexing and processing of various types of spatial queries to support reasoning of spatial information. Our solutions are implemented in the context of a prototype system called SAT (spatial awareness from text)that models and represents (potentially uncertain) event locations described in free text and incorporates several types of spatial queries of interest in SA applications. We demonstrate SAT in the context of 2 real-world applications that derive spatial information from text at different phases of the disaster response process.