Explainable Tracking of Political Violence Using the Tsetlin Machine

In this paper we introduce a framework that utilizes an architecture based on the Tsetlin Machine to output explainable rules for the prediction of political violence. The framework includes a data processing pipeline, modeling architecture, and visualization tools for early warning about notable events. We conducted an experimental study to explain and predict a one of the most notable events, - a civil war. We observed that the rules that we produced are consistent with theories that emphasize the continuing risks that accumulate from a history of conflict as well as the stickiness of civil war.