A Text Mining System for Modeling Social Dynamics in Groups

Award Information
Agency:
Department of Defense
Branch
Air Force
Amount:
$150,000.00
Award Year:
2012
Program:
SBIR
Phase:
Phase I
Contract:
FA8650-12-M-6345
Agency Tracking Number:
F121-033-2029
Solicitation Year:
2012
Solicitation Topic Code:
AF121-033
Solicitation Number:
2012.1
Small Business Information
Intelligent Automation, Inc.
MD, Suite 400, Rockville, MD, 20855-2737
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
Y
Duns:
161911532
Principal Investigator:
Xiong Liu
Research Scientist
(301) 294-4629
xliu@i-a-i.com
Business Contact:
Mark James
Director, Contracts and Proposals
(301) 294-5221
mjames@i-a-i.com
Research Institution:
Stub




Abstract
ABSTRACT: Text-based communication can reveal important information about people"s thoughts, motives, and relationships with others. However, developing objective, efficient, and unobtrusive tools to determine group intent and forecast future behaviors remains a significant challenge. We propose a novel framework for extracting metrics of group dynamics from discourses and producing predictive models of social processes among individuals and organizations. This framework is a large-scale, dynamic approach for maximizing the ability of intelligence analysts to analyze text-based communication to assess social dynamics for a given group and predict current belief states and likely intended actions. BENEFIT: IAI"s proposed technology can be directly applied to the military and intelligence contexts, such as domestic and international security regulations. The correlation and reasoning capabilities can help analysts understand and forecast group behaviors or regions that are prone to conflicts. Our methods can provide very fast and efficient markers of basic social dynamics, and these tools will help analysts understand past actions and cognitions of individuals and groups. In the commercial sector we anticipate that the resulting technology will have wide applications in remote event monitoring, crime identification and prevention, corporate security, law enforcement, and business negotiations.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government