MArCo: Building an Artificial Conflict Mediator to Support Group Planning Interactions

Issue title: "Caring for the Learner" in honour of John Self

Article type: Research Article

Authors: Tedesco, Patricia Azevedo

Affiliations: Centro de Informática - UFPE. Av. Prof. Luiz Freire, s/n. Cidade Universitária, Recife-PE. CEP: 50740-540, Brazil. pcart@cin.ufpe.br

Abstract: The emphasis on building co-operative/collaborative environments has brought out the matter of group interactions. This, in its turn, has highlighted the issue of conflicts, inherent to group problem solving. If well employed, conflicts can act as triggers of cognitive changes, and thus help to refine the group's solution to the task. In this paper, we present a computational framework for detecting and mediating Meta-Cognitive conflicts. The theoretical framework presented here enables a computational system to analyse the ongoing interaction, to detect and mediate conflicts. In order to do so, we consider our model of strategic changes, a model of the group, and the history of the interaction. The objective of the mediation is to suggest courses of action that provoke articulation and reflection, and thus lead to more refined solutions. In order to diagnose which changes are happening to the group plan we have built a model of strategic operations, which describes what types of changes happen to a plan as well as how changes to one component of the strategy (beliefs, intentions, ordering relations, context beliefs and goals) impact the other ones. MArCo, our prototype embedding the artificial conflict mediator, shows how our conceptual framework has been put to practical use.

Journal: International Journal of Artificial Intelligence in Education, vol. 13, no. 1, pp. 117-155, 2003