An Argument Structure Abstraction for Bayesian Belief Networks: Just Outcomes in On-line Dispute Resolution

Muecke, N. and Stranieri, A.

    There are many different approaches for settling disputes on-line, such as simple email systems, fixed bid systems and intelligent systems. However, to date there have been no attempts to integrate decision support methods into the dispute resolution process for the purpose of supporting outcomes that are consistent with judicial reasoning. This paper describes how a model of judicial reasoning can be used to assist divorcees with the resolution of property issues online, in a manner that is consistent with decisions a judge would make if the matter was heard in Court. The approach uses an argument based model of the discretionary nature of decisions made by judges in Australian Family Law. This is integrated with a protocol for online dispute dialogue. Predictions of the likelihood of alternates outcomes is achieved with a series of Bayesian Belief Networks.
Cite as: Muecke, N. and Stranieri, A. (2007). An Argument Structure Abstraction for Bayesian Belief Networks: Just Outcomes in On-line Dispute Resolution. In Proc. Fourth Asia-Pacific Conference on Conceptual Modelling (APCCM2007), Ballarat, Australia. CRPIT, 67. Roddick, J. F. and Hinze, A., Eds. ACS. 35-40.
pdf (from crpit.com) pdf (local if available) BibTeX EndNote GS