A Multi-agent Approach to the Design of Peer-help Environments

This paper presents a multi-agent approach to design of adaptive distributed collaborative and peer help environments, which addresses a number of challenges: locating appropriate human and electronic resources depending on the help-request, motivating users to help each other, providing design approaches that are easily extendible "in-depth" and "in-breadth". We explore the notion of modelling user social characteristics, that is a "social user model", which is as important as a cognitive user model in supporting user collaboration and peer help. We show how adaptive behaviour (location of resources) of the heterogeneous distributed system I-Help can arise as a result of negotiation of goal-oriented autonomous cognitive agents. We are introducing an economic model in order to motivate users to collaborate and provide peer help while protecting helpers from getting overloaded with requests. Finally, we propose using multi-agent based simulation tools to simulate and test various economic models with respect to their appropriateness in the context of a learning environment.