Probabilistic user modeling in the presence of drifting concepts
PAKDD'10 Proceedings of the 14th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part I
| Hi-index | 0.00 |
The aim of a multi-agent system behavioral analysis is to understand individual and collective behavior of agents. This is useful for improving agents efficiency or studying an unknown system. It is a difficult problem for many reasons such as systems heterogeneity and the large set of events that arise at any time. In this paper, we propose a dynamic agents model relying on the recently introduced notion of semi-structured data. This paradigm allows to store and query under a homogeneous form information about structure, contents and evolution of data. We show how to easily query knowledge on entities behavior and to classify them by detecting their respective roles. We also discuss the possibility to integrate the model into an intelligent architecture.