Entity Profiling for Intelligence Using the Graphical Overview of Social and Semantic Interactions of People (GOSSIP) Software Tool

PDF

Authors
  1. Kwantes, P.
  2. Terhaar, P.
Corporate Authors
Defence R&D Canada - Toronto, Toronto ONT (CAN)
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-defined 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.

Il y a un résumé en français ici.

Keywords
Profiling;Intelligence;Target audience analysis;Influence activities analysis;Latent Semantic Analysis
Report Number
DRDC-TORONTO-TR-2010-188 — Technical Report
Date of publication
30 Nov 2010
Number of Pages
33
DSTKIM No
CA035258
CANDIS No
535013
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: