This paper briefly describes AMANDA(1), a framework for mediating collect ve discussions in distance learning environments. The objective of this framework is to help tutors achieve better results from group discussions and improve knowledge transfer among the participants. The overall idea is to organize the group discussion in an argumentation tree and involve the participants in successive discussion activities. The coordination of the discussion is made by a set of intelligent mechanisms which reason over the discussion and propose new interact ons among the participants. AMANDA advances the discussion by generating progressive discussion cycles until a desired set of target conditions arc observed. At each discussion cycle, the system redistributes discussion tasks among the participants to ensure a desired degree of agreement and participation among them. In this short paper we describe the underlying coordination principles and the use of knowledge models for producing natural language questions.
展开▼