terrorist_attacks — Terrorist attacks, LINQS (2005)

Description

Networks of terrorist attacks from the Profiles in Terror (PIT) knowledge base of the MIND Lab at the University of Maryland, as distributed by the LINQS group (Zhao, Sen and Getoor) as a benchmark for relational (collective) classification. PIT was a semantic knowledge base of terrorism intelligence (attacks, terrorists and terrorist organisations) extracted from sources such as news media reports. The dataset contains 1293 terrorist attacks, each classified into one of six types.

Nodes are attacks, and there are two networks:

colocation: an edge connects two attacks that occurred in the same geographical location.
colocation_same_org: an edge connects two attacks that occurred in the same location and were carried out by the same organization (a subset of the edges of colocation).

The networks have the following vertex properties: name, the identifier of the attack in PIT (for most attacks, the name of the organization responsible, or "Unknown", followed by the date in the format YYYYMMDD; the remaining identifiers are URLs of PIT documents); attack_type, the class of the attack (arson, bombing, kidnapping, NBCR attack, i.e. nuclear, biological, chemical or radiological, weapon attack, or other attack); and features, a vector of 106 binary attributes of the attack (according to the source, including information such as the year of the attack and keywords from its description; their meanings are not given in the data). The same two networks, restricted to the attacks with at least one edge, are also distributed by the UCINET datasets collection as "Linux Terrorists".

Tags

Social Offline Unweighted Metadata

Citation

B. Zhao, P. Sen, and L. Getoor, "Event classification and relationship labeling in affiliation networks." Proceedings of the Workshop on Statistical Network Analysis (SNA) at the 23rd International Conference on Machine Learning (ICML) (2006) www.cs.umd.edu

Upstream URL OK

https://linqs.org/datasets/

Networks

Tip: click on a column header to sort the list, or hover over it for a description.

Column legend

$\left<k\right>$: Mean degree
$\sigma_k$: Standard deviation of the degrees
$\lambda_h$: Largest eigenvalue of the Hashimoto (non-backtracking) matrix
$\tau$: Random walk mixing time
$r$: Degree assortativity
$c$: Global clustering coefficient
$\oslash$: (Pseudo-) diameter
$S$: Relative size of the largest component
NPs: Node properties
EPs: Edge properties

Name	Nodes	Edges	$\left<k\right>$	$\sigma_k$	$\lambda_h$	$\tau$	$r$	$c$	$\oslash$	$S$	Kind	Mode	NPs	EPs	gt	GraphML	GML	csv
colocation	1,293	3,172	4.91	10.13	47.00	2.96	1.00	1.00	3	0.04	Undirected	Unipartite	name attack_type features		19 KiB	32 KiB	31 KiB	21 KiB
colocation_same_org	1,293	571	0.88	2.68	14.00	0.02	1.00	1.00	1	0.01	Undirected	Unipartite	name attack_type features		17 KiB	24 KiB	24 KiB	14 KiB