Computational approach and cognitive assistant for evidence-based reasoning in intelligence analysis

Abstract

This paper presents a computational approach to intelligence analysis and its current implementation into a cognitive assistant called Disciple-CD. Intelligence analysis is viewed as ceaseless discovery of evidence, hypotheses, and arguments in a non-stationary world, involving cooperative processes of evidence in search of hypotheses, hypotheses in search of evidence, and evidentiary tests of hypotheses. Disciple-CD helps intelligence analysts formulate hypotheses, develop arguments that reduce complex hypotheses to simpler and simpler ones, collect evidence to evaluate the simplest hypotheses, assess the relevance, believability, and inferential force of evidence, and finally the likeliness of the hypotheses.