An Ontological Framework to Facilitate Early Detection of 'Radicalization' (OFEDR)-A Three World Perspective.

Linda Wendelberg

doi:10.3390/jimaging7030060

Abstract

This paper presents an ontology that involves using information from various sources from different disciplines and combining it in order to predict whether a given person is in a radicalization process. The purpose of the ontology is to improve the early detection of radicalization in persons, thereby contributing to increasing the extent to which the unwanted escalation of radicalization processes can be prevented. The ontology combines findings related to existential anxiety that are related to political radicalization with well-known criminal profiles or radicalization findings. The software Protégé, delivered by the technical field at Stanford University, including the SPARQL tab, is used to develop and test the ontology. The testing, which involved five models, showed that the ontology could detect individuals according to “risk profiles” for subjects based on existential anxiety. SPARQL queries showed an average detection probability of 5% including only a risk population and 2% on a whole test population. Testing by using machine learning algorithms proved that inclusion of less than four variables in each model produced unreliable results. This suggest that the Ontology Framework to Facilitate Early Detection of ‘Radicalization’ (OFEDR) ontology risk model should consist of at least four variables to reach a certain level of reliability. Analysis shows that use of a probability based on an estimated risk of terrorism may produce a gap between the number of subjects who actually have early signs of radicalization and those found by using probability estimates for extremely rare events. It is reasoned that an ontology exists as a world three object in the real world.

Highlights

Published: 22 March 2021In the fall of 2019, Philip Manshaus killed his sister and, on the same day, attacked a mosque in Bærum, Norway [1]
Analysis shows that use of a probability based on an estimated risk of terrorism may produce a gap between the number of subjects who have early signs of radicalization and those found by using probability estimates for extremely rare events
This process will be shown by using the software Protégé, delivered by the technical field at Stanford University, and Waikato Environment for Knowledge Analysis (Weka), developed at the University of Waikato, New Zealand [55,56,57]

Summary

Introduction

Published: 22 March 2021In the fall of 2019, Philip Manshaus killed his sister and, on the same day, attacked a mosque in Bærum, Norway [1]. One example is neurophysiological and neuropsychological indicators that are most frequently developed by medicine and psychology Another example is indicators related to terrorist acts that are developed by law enforcement agencies (LEA) and the defense sector. These disciplines operate in real life as separate silos that are largely prevented from cooperating because of basic regulations, such as confidentiality and organization. Another issue is that many institutions, such as schools, work-life, universities, parents, hospitals, etc., require knowledge and indicators that are reserved for the police and defense. One possible reason for the Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations

Objectives

Methods

Results

Discussion

Conclusion