Context-based and Explainable Decision Making with Argumentation

Zhiwei Zeng, Xiuyi Fan, Chunyan Miao, Cyril Leung, Jing Jih Chin, Yew-Soon Ong

Abstract: Argumentation-based approaches to decision making have gained considerable research interest, due to their ability to select and justify decisions. In order to make better decisions, context is a key piece of information that needs to be considered. However, most existing argumentation-based models and frameworks have not modelled or reasoned with context explicitly. In this paper, we present a new argumentation-based approach for making context-based and explainable decisions. We propose a graphical representation for modelling decision problems involving varying contexts, Decision Graphs with Context (DGC), and a reasoning mechanism for making context-based decisions which relies on the Assumption-based Argumentation formalism. Based on these constructs, we introduce two types of explanations, argument explanation and context explanation , identifying the reasons for the decisions made from an argument-view and a context-view respectively.