Data-driven diffusion modeling to examine deterrence

The combination of social network extraction from texts, network analytics to identify key actors, and then simulation to assess alternative interventions in terms of their impact on the network is a powerful approach for supporting crisis de-escalation activities. In this paper, we describe how researchers used this approach as part of a scenario-driven modeling effort. We demonstrate the strength of going from data-to-model and the advantages of data-driven simulation. We conclude with a discussion of the limitations of this approach for the chosen policy domain and our anticipated future steps.