Visual Analysis of Entity Relationships in Global Terrorism Database

With the increase of terrorist activity around the world, it has become more important than ever to analyze and understand these activities over time. Although the data on terrorist activities are detailed and relevant, the complexity of the data has rendered the understanding and analysis difficult. We present a visual analytical approach to effectively identify related entities such as terrorist groups, events, locations, etc. based on a 2D layout. Our methods are based on sequence comparison from bioinformatics, modified to incorporate the element of time. By allowing the user the freedom to link entities by their activities over time, we provide a new framework for comparison of event sequences. Our scoring mechanism is robust and flexible, giving the user the flexibility to define the extent to which time is considered in aligning entities. Incorporated with high interactivity, the user can efficiently navigate through tens of thousands of records recorded in over a hundred dimensions of data by choosing combinations of categories to examine. Exploration of the terrorist activities in our system reveals relationships between entities that are not easily detectable using traditional methods.

Alex Godwin, Remco Chang, Robert Kosara, and William Ribarsky, Visual Analysis of Entity Relationships in Global Terrorism Database, SPIE Defense and Security, 2008.

@inproceedings{Godwin:SPIE:2008,
	year = 2008,
	title = {Visual Analysis of Entity Relationships in Global Terrorism Database},
	author = {Alex Godwin and Remco Chang and Robert Kosara and William Ribarsky},
	booktitle = {SPIE Defense and Security},
	abstract = {With the increase of terrorist activity around the world, it has become more important than ever to analyze and understand these activities over time. Although the data on terrorist activities are detailed and relevant, the complexity of the data has rendered the understanding and analysis difficult. We present a visual analytical approach to effectively identify related entities such as terrorist groups, events, locations, etc. based on a 2D layout. Our methods are based on sequence comparison from bioinformatics, modified to incorporate the element of time. By allowing the user the freedom to link entities by their activities over time, we provide a new framework for comparison of event sequences. Our scoring mechanism is robust and flexible, giving the user the flexibility to define the extent to which time is considered in aligning entities. Incorporated with high interactivity, the user can efficiently navigate through tens of thousands of records recorded in over a hundred dimensions of data by choosing combinations of categories to examine. Exploration of the terrorist activities in our system reveals relationships between entities that are not easily detectable using traditional methods.},
}