White Papers
Rosoka is proud to be partnered with Norwich University, whose students have recently been published in "The Journal on Terrorism and Security Analysis."
From Strategy to Tactics: Analyzing al-Qaeda in the Arabian Peninsula’s Inspire Magazine, Issue 17
Anthony Aversano and Timothy Weinhold
Published Spring 2018
Introduction
This article analyzes Inspire Magazine issue 17 – Al Qaeda’s propaganda magazine –from its strategic ideological preaching to its tactics. As Al Qaeda in the Arabian Peninsula (AQAP) continues to rally and call to action those willing to detest all enemies of Islam, it is vitally important to explore how the organization continues to recruit at the individual level using Inspire Magazine. We examine the magazine’s format and content to better understand how a reader could potentially sympathize with their cause(s), internalize their ideology, and implement the proposed tactics. Using Rosoka, a natural language processing (NLP) software, we stratify our analysis into a strategic and tactical prospective. The strategic analysis focuses on diagnostic frames, ideological concepts, and image analysis, while the tactical analysis explores entity organizations, persons, weapons, and targets. As a tactic, Inspire 17 prioritizes targeting means of transportation with a focus on derailing trains using a simplistic train derailment tool.2 Derived from the intelligence provided in the magazine, our team presents a worst-case scenario to bring to light the potential lethal implications. In conclusion, we discuss four recommended courses of action aimed at both the prevention of train derailments and the monitoring of Inspire Magazine publications.
Accuracy Metrics for Entity Extraction
Kelly Enochson, PhD; Gregory Roberts
Rosoka Software, Inc. 950 Herndon Parkway, Suite 370, Herndon, VA 20170
Published January 2017
Abstract
Entity extraction software is typically evaluated based on the widely-accepted accuracy metrics of precision, recall, and F-measure. These metrics are certainly useful but limited in their scope. Additional factors including the types of errors, the cost of different error types, the facility of making changes to the system, and the efficiency of the system compared to human tagging should also be incorporated when evaluating entity extraction software. This paper illustrates the need for these additional factors and demonstrates how they can be implemented in evaluation.
Analyzing Newswire and Social Media Data Using Multi-Vector Sentiment Analysis
Kelly Enochson, PhD; Gregory Roberts; Michael Sorah; Jamie Thompson
Rosoka Software, Inc., 950 Herndon Parkway, Suite 280, Herndon, VA 20170
Published September 2016
Abstract
The vast amount of written text available on the Internet provides a treasure trove of information for intelligence and security analysts, but only if the useful data can be quickly identified among all the irrelevant information. Many analytical tools available provide information about the sentiment of written texts; however, these tools typically utilize only one measure of sentiment in their metrics. Rosoka Software leverages psycholinguistic research across multiple sentiment vectors to provide precise information about an author’s language and pinpoint documents that do not follow predicted patterns. Rosoka’s multi-vector sentiment analysis uses four metrics to help analysts identify outliers in their data, recognize heightened emotional language, sort data by media type, and subset large data sets into only the documents that require further assessment.
Parserless Extraction; Using a Multidimensional Transient State Vector Machine
Michael Sorah
Rosoka Software, Inc., 950 Herndon Parkway, Suite 280, Herndon, VA 20170
Published March 2016