An Analyst’s Geospatial and Ontological Assistant

Abstract

We discuss an Intelligence Analyst’s Geospatial and Ontological Assistant (IAGOA) under development that associates an intelligence analyst’s understanding of an agent’s activities with the geospatial features of the area of operation where they take place. Activities are identified with frames for the corresponding verbs from the FrameNet lexical database. A modeler, using the FrameNet OWL distribution, produces software used by the analyst to update a KML file with annotations identifying instantiations of the frames elements of the relevant frames. The Google Earth API is used for rendering KML files and scripting. The agent is tracked and the analyst’s conjecture of its activity is simulated; the analyst can redo her conjecture if need be. IAGOA’s FrameNet-based approach instantiates concepts inherent in language, making explicit the activities and the constellation of role-fillers involved in these activities.