Real Time User Context Modeling for Information Retrieval Agents (pdf )

Bauer, T. and Leake, D., Real Time User Context Modeling for Information Retrieval Agents, Proceedings of the 2001 ACM CIKM: Tenth International Conference on Information and Knowledge Management , Association for Computing Machinery, 2001.


The success of personal information agents depends on their ability to provide task-relevant information. This paper presents WordSieve, a new algorithm that generates context descriptions to guide document indexing and retrieval. WordSieve exploits information about the sequence of accessed documents to identify words which indicate a shift in context. % This is done in real time without requiring the % user to rank pages or provide other kinds of explicit feedback, and without % requiring analysis of the entire potential document set. We have tested WordSieve in a personal information agent, Calvin, which monitors a user's document access, generates a representation of the user's task context, indexes the resources consulted, and presents recommendations for other resources that were consulted in similar prior contexts. In initial experiments, WordSieve outperforms \textit{term frequency/inverse document frequency} at matching documents to hand-coded vector representations of the task contexts in which they were originally consulted, where the task context representations are term vectors representing a specific search task given to the user.

See for additional publications in the Artificial Intelligence/Cognitive Science report and reprint archive maintained by David Leake.