We presented an approach to building WWW-based managers of online free-text expertise, called Information Exchange systems. The objective of the Information Exchange technology is to meet the growing need of organizations to answer clients' questions quickly and to use their experts efficiently.
We described CIE, an Information Exchange system that manages the online expertise of the University of Chicago's Department of Computer Science and acts as an intermediary between its clients and experts.
We presented the indexing and retrieval techniques and term weight metrics that support interactions and collaborations in question-answering. Our term weight metric combines morphological analysis, spreading activation, and two statistical techniques of the vector space model of retrieval. We argued that to support adequate interactions with the experts, relevance feedback needs to be complemented with negative evidence acquisition.
Our approach is fundamentally human-centered. We focus on an interactive and collaborative behavior that already exists, i.e. interactive and collaborative question-answering in organizations, and develop a technology that supports it for the benefit of both clients and experts.