Entity Profiling for Intelligence Using the Graphical Overview of Social and Semantic Interactions of People (GOSSIP) Software Tool
Abstract
GOSSIP is a software program designed to help analysts find important entities discussed in a document collection and uncover the nature of the connections among them. It uses computational model of semantic system to create ?meaning? representations of all the words/terms it encounters in the collection?including proper names. In this report we demonstrate that the semantic representation of proper names discussed in a document collection can be usefully queried to find out how strongly the entities are associated with a set of user−define qualities or concepts. We recommend that GOSSIP be trailed in contexts where intelligence analysts or those engaged in influence activities are forced to quickly develop situational awareness about individuals or organizations in a domain from large collections of relevant documents.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 2010
- Accession Number
- ADA551103
Entities
People
- Peter Kwantes
- Phil Terhaar
Organizations
- Defence Research and Development Canada