Find in Library

This paper explores the computation of explanations in the specific context of abstract argumentation. The explanations that we define are designed to be visual, in the sense that they take the form of subgraphs of the argumentation graph. Moreover, these explanations rely on the modular aspects of abstract argumentation semantics and can consequently be either aggregated or decomposed. We investigate graph properties of these explanations, and their adequacy to desirable explanatory criteria.