VIOLENT FRAMES IN ACTION

Journal Article · Thu Nov 17 00:00:00 EST 2011 · Dynamics of Asymmetric Conflict

DOI:https://doi.org/10.1080/17467586.2011.627933· OSTI ID:1029864

Sanfilippo, Antonio P; McGrath, Liam R; Whitney, Paul D

We present a computational approach to radical rhetoric that leverages the co-expression of rhetoric and action features in discourse to identify violent intent. The approach combines text mining and machine learning techniques with insights from Frame Analysis and theories that explain the emergence of violence in terms of moral disengagement, the violation of sacred values and social isolation in order to build computational models that identify messages from terrorist sources and estimate their proximity to an attack. We discuss a specific application of this approach to a body of documents from and about radical and terrorist groups in the Middle East and present the results achieved.

• Research Organization: Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1029864
• Report Number(s): PNNL-SA-77551; TRN: US201123%%444
• Journal Information: Dynamics of Asymmetric Conflict, Vol. 4, Issue 2; ISSN 1746-7586
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE
ARTIFICIAL INTELLIGENCE
COMPUTERIZED SIMULATION
INFORMATION RETRIEVAL
MIDDLE EAST
DATA ACQUISITION
DATA ANALYSIS
SABOTAGE