MOSAIC: criminal network analysis for multi-modal surveillance and decision support

With increasing complexity of the social systems under surveillance, demand grows for automated tools which are able to support end users in making sense of situational context from the amount of available data and incoming data streams. This paper presents MOSAIC (Multi-Modal Situation Assessment and Analytics Platform), a semantically integrated system which aims at exploiting multi-modal data analysis comprising advanced tools for text and data mining, criminal network analysis, and decision support. The aim is to provide, from an enriched context, an understanding of behaviour of the system under surveillance thus supporting authorities in their decision making processes. Specific measures and algorithms have been developed to support analysts in retrieving, analysing, and disrupting criminal networks, identifying offenders that pose the greatest harm aligned with domain-specific strategies, as well as enabling the investigation of intervention strategies. A case study is provided in order to illustrate the system in practice.