Show Abstract
Individuals, organizations, and devices are now interconnected to an unprecedented degree, forcing identity risk analysts to redefine “identity” in such contexts and explore new techniques for analyzing expanding threat contexts. Major hurdles to modeling in this field include a lack of publicly available data due to privacy and safety concerns, as well as the unstructured nature of incident reports. Thus, this report uses news story text mining to develop a new system for strengthening identity risk models. The NewsFerret system collects and analyzes stories about identity theft, establishes semantic relatedness measures between identity concept pairs, and supports analysis of those measures with reports, visualizations, and relevant news stories. Risk analysts can utilize the resulting analytical models to define and validate identity risk models.
CITATION:
Golden, R. and K.S. Barber, International Journal of Computer and Information Technology (IJCIT), Vol. 3(5), pp. 850-859, 2014.