The Geometrical Shapes of Violence: Predicting and Explaining Terrorist Operations Through Graph Embeddings

Gian Maria Campedelli, Janet Layne, Jack Herzoff, Edoardo Serra

Research output: Contribution to journalArticlepeer-review

Abstract

Behaviours across terrorist groups differ based on a variety of factors, such as groups’ resources or objectives. We here show that organizations can also be distinguished by network representations of their operations. We provide evidence in this direction in the frame of a computational methodology organized in two steps, exploiting data on attacks plotted by Al Shabaab, Boko Haram, the Islamic State and the Taliban in the 2013–2018 period. First, we present LabeledSparseStruct, a graph embedding approach, to predict the group associated with each operational meta-graph. Second, we introduce SparseStructExplanation, an algorithmic explainer based on LabeledSparseStruct, that disentangles characterizing features for each organization, enhancing interpretability at the dyadic level. We demonstrate that groups can be discriminated according to the structure and topology of their operational meta-graphs, and that each organization is characterized by the recurrence of specific dyadic interactions among event features.

Original languageAmerican English
JournalComputer Science Faculty Publications and Presentations
StatePublished - 1 Apr 2022

Keywords

  • complex networks
  • conflict
  • graph learning
  • neural networks
  • political violence
  • security

EGS Disciplines

  • Computer Sciences

Fingerprint

Dive into the research topics of 'The Geometrical Shapes of Violence: Predicting and Explaining Terrorist Operations Through Graph Embeddings'. Together they form a unique fingerprint.

Cite this