Wassila Ouerdane: Towards Interactive Explanations and Recommandations for Decision Support

In a decision-aiding process, to provide convincing recommendations that a decision-maker can fully understand and accept, a decision-aider must often engage in interaction and consider the decision-maker’s responses. This feedback can lead to revising the model used to represent the decision-maker’s preferences. Our objective in this work is to equip an artificial decision-aider with this adaptive behavior. To do that, we build, on the one hand, on decision theory to propose a principled way to select decision models. On the other hand, we grounded on argumentation-based dialogue to support such an interaction and to justify the outcomes. Argumentation theory is a rich, interdisciplinary area of research across AI, philosophy, communication studies, linguistics and psychology. It can be used to specify autonomous agents reasoning and to facilitate agents interaction. More recently, argumentation theory has received particular attention in the field of XAI, as it naturally provides a means of making decision mechanisms transparent.