The
IEXTREME project is a trans-Atlantic collaborative project, funded by the
U.S. Office of Naval Research. The
project is a collaborative venture between the University of Southampton,
Applied Research Associates and
Rababy & Associates LLC,
with Applied Research Associates acting as the prime contractor. The main
goal of the IEXTREME project is to develop a better understanding of the
ideological enablers associated with the behaviour of terrorist and insurgent
groups. The
National Military Strategic Plan for the War on Terrorism identifies
extremist ideology as the enemy’s strategic center of gravity, and the
Department of Defense (DoD) plays
a significant role in establishing an environment unfavourable to extremist
ideas, terrorist recruitment, and support. In spite of this, however, we
have, as yet, little understanding of the specific ways in which extremist
ideology contributes to various forms of terrorist action. IEXTREME aims
to address this shortcoming by combining state-of-the-art approaches to
cultural modelling with a variety of advanced knowledge technologies. The
project builds on the scientific and technical outcomes of a number of previous
projects, including
SEMIOTIKS,
MIMEX,
ITA,
ArtEquAKT
and AKT.
The IEXTREME project is broken down into a number of separate, but inter-dependent,
research and development activities:
Cultural Model Development: Using state-of-the-art
approaches to cultural model development, Applied Research Associates
will develop qualitative models of both extremist and moderate religious
groups. The aim here is to provide a cognitive characterization of groups
in terms of their commitment to terrorist activities. Clearly, extremist
and moderate groups can be distinguished in terms of their decision
to commit acts of terrorism, but to what extent can this commitment
be accounted for in terms of the specific beliefs and values of the
group members? Furthermore, what role do beliefs and values play in
legitimating terrorist action? Do specific beliefs serve to reinforce
extremism by prohibiting a consideration of alternative ideologies?
And can pre-existing beliefs effectively inoculate a religious community
against the adoption of extremist ideologies? These are the kind of
questions that the cultural modelling activity intends to explore. In
developing cultural models, Applied Research Associates will rely on
a technique called Cultural Network Analysis (CNA). CNA is a technique
for developing cultural models that draws on ideas,
methods and techniques from a variety of disciplines, including
naturalistic decision making, cognitive anthropology,
cognitive psychology, and decision analysis. CNA was developed
by Applied Research Associates, and it has been used in a variety of
application contexts. For example, it has been used to support the identification
of cultural differences between US and UK military planners, to analyse
the decision making processes of Middle Eastern crowd members, and to
model the decision-making frameworks associated with nuclear terrorism.
Cultural Ontology Development: Cultural models
are intended to represent a group’s causally-relevant beliefs and values
as they relate to a specific decision outcome, e.g. the decision to
commit acts of terrorism. The conventional way of communicating such
models is, however, somewhat informal, and this prohibits the effective
exploitation of the models in automated processes. The aim of the cultural
ontology development activity is to develop cultural ontologies that
represent the content of cultural models in a form that is much more
amenable to machine-based processing. The activity also seeks to extend
and adapt the cultural ontologies developed in previous projects, such
as the MIMEX
project.
Cultural Analysis System (CAS) Development: The
University of Southampton will act as technical lead on the development
of a technical demonstrator system to support the analysis of culture-relevant
resources on the World Wide Web. The system will also be used to support
a number of empirical evaluation studies. The CAS comprises a suite
of knowledge processing and information visualization technologies.
Together these technologies deliver the following capabilities:
Ontology Visualization and Editing: The CAS
will support the visualization and editing of cultural ontologies
by providing access to state-of-the-art semantic browser interfaces
and controlled natural language editors.
Resource Classification: Building on the scientific
and technical outcomes of the
SEMIOTIKS
project, the CAS will include a resource classification capability
that capitalizes on the availability of semantically-enriched meta-data
characterizations of resource content.
Knowledge Extraction: The IEXTREME project
will incorporate information extraction capabilities developed in
the course of previous projects. One of these capabilities is demonstrated
by the
ArtEquAKT
initiative, which was undertaken as part of the
Advanced Knowledge Technologies
(AKT) programme. ArtEquAKT relied on an ontology of artists and
artistic works to support the extraction of relational information
from a number of Web-based resources. A similar capability will
be developed as part of the IEXTREME project to support the extraction
of culture-relevant information from both Web-based and archival
resources.
Empirical Evaluation: The IEXTREME project includes
a number of empirical evaluation activities which will be undertaken
to assess the performance of the CAS's knowledge extraction and resource
classification capabilities in the cognitive anthropological domain.
Together the scientific outcomes of the IEXTREME project are expected
to deliver improvements in our understanding of the way in which extremist
ideological influences support the behaviour of terrorist and insurgent
groups. The project will also deliver a number of important technical outcomes.
These include state-of-the-art approaches to resource classification, semantic
annotation, knowledge extraction, and information visualization; ontologies
to support the representation of culture-relevant information; and tools
to support the entry and editing of cultural model content. All these outcomes
will contribute to our understanding of the ideological enablers associated
with the behaviour of terrorist and insurgent groups. They also provide
insights into how the decision-making processes of terrorist organizations
might be subverted as part of future counter-terrorism initiatives.