Spotting terrorists by learning behavior-aware heterogeneous network embedding

Heterogeneous network is a useful data representation in depicting complex interactions among multi-typed entities and relations. In this work, by representing criminal and terrorism activities as a heterogeneous network, we propose a novel unsupervised method, Outlier Spotting with behavior-aware Network Embedding (OSNE), to identify terrorists among potential criminals. The basic idea of OSNE is to exploit high-order relation paths for translation-based embedding learning, and distinguish same-type entities based on behavior penalty and type-aware negative sampling. We evaluate the effectiveness of OSNE using six criminal network datasets provided by DARPA, and make comparison with strong competitors. The results exhibit the promising performance of OSNE.