Intelligent Information Gathering Using Decision Models

This paper describes an architecture for the next generation of information gathering systems. The paper is based on a research proposal whose goal is to exploit the vast amount of information sources available today on the NII including a growing number of digital libraries, independent news agencies, government agencies, as well as human experts providing a variety of services. The large number of information sources and their different levels of accessibility, reliability and associated costs present a complex information gathering coordination problem. We outline the structure and components of an information gathering system that uses an explicit representation of the user’s decision model in order to organize its activity. Within this framework, information gathering planning is performed based on its marginal contribution to the user’s decision quality.