A Computational Argumentation Framework for Agent Societies

Abstract

Starting from the idea that the social context of agents determines the way in which agents can argue and reach agreements, this context should have a decisive influence in the computational representation of arguments. In this report, we advance research in the area of computational frameworks for agent argumentation by proposing a new argumentation framework (AF) for the design of open MAS in which the participating software agents are able to manage and exchange arguments between themselves taking into account the agents¿ social context. In order to do this, we have analysed the necessary requirements for this type of framework 1 and taken into account them in the design of our framework. Also, the knowledge resources that the agents can use to manage arguments in this framework are presented in this work. In addition, if heterogeneous agents can interact in the framework, they need a common language to represent arguments and argumentation processes. To cope with this, we have also designed an argumentation ontology to represent arguments and argumentation concepts in our framework.