User interactions with everyday applications as context for just-in-time information access

ABSTRACT

Our central claim is that user interactions with everyday productivity applications (e.g., word processors, Web browsers, etc.) provide rich contextual information that can be leveraged to support just-in-time access to task-relevant information. We discuss the requirements for such systems, and develop a general architecture for systems of this type. As evidence for our claim, we present Watson, a system which gathers contextual information in the form of the text of the document the user is manipulating in order to proactively retrieve documents from distributed information repositories. We close by describing the results of several experiments with Watson, which show it consistently provides useful information to its users.

REFERENCES

• 1: Alexa. http://www.alexa.corn/
• 2: Alta Vista. http://www.altavista.comt
• 3: Badue, C., Vaz, W., and Albuquerque, E. Using an Automatic Retrieval System in the Web to Assist Cooperative Learning. In Proc. 1998 World Conference of the Www, Internet and Intranet. AACE Press, 1998.
• 4: Daniel Billsus , Michael J. Pazzani, A personal news agent that talks, learns and explains, Proceedings of the third annual conference on Autonomous Agents, p.268-275, April 1999, Seattle, Washington, United States [doi>10.1145/301136.301208]
• 5: Bradshaw, S., and Hammond, K. J. Mining Citation Text as Indices for Documents. In Proceedings of the ASIS 1999 Annual Conference. Information Today, Inc., Medford NJ, 1999.
• 6: Budzik, J, Hammond, K., Marlow, C., and Scheinkman, A. Anticipating Information Needs: Everyday Applications as Interfaces to Internet Information Sources. In Proceedings of WebNet-98, Conference of the WWW, Internet and Intranet. AACE Press, 1998.
• 7: Budzik, J., and Hammond K. Q&A: A system for the Capture, Organization and Reuse of Expertise. In Proceedings of the ASIS 1999 Annual Conference. Information Today, Inc., Medford NJ, 1999.
• 8: Budzik, J., and Hammond, K. Watson: Anticipating and Contextualizing Information Needs. In Proceedings of the ASIS 1999 Annual Conference. Information Today, Inc., Medford NJ, 1999.
• 9: Liren Chen , Katia Sycara, WebMate: a personal agent for browsing and searching, Proceedings of the second international conference on Autonomous agents, p.132-139, May 10-13, 1998, Minneapolis, Minnesota, United States [doi>10.1145/280765.280789]
• 10: Isaac Cheng , Robert Wilensky, An Experiment in Enhancing Information Access by Natural Language, University of California at Berkeley, Berkeley, CA, 1997
• 11: Jeffrey Dean , Monika R. Henzinger, Finding related pages in the World Wide Web, Proceeding of the eighth international conference on World Wide Web, p.1467-1479, May 1999, Toronto, Canada
• 12: S. T. Dumais , G. W. Furnas , T. K. Landauer , S. Deerwester , R. Harshman, Using latent semantic analysis to improve access to textual information, Proceedings of the SIGCHI conference on Human factors in computing systems, p.281-285, May 15-19, 1988, Washington, D.C., United States [doi>10.1145/57167.57214]
• 13: Susan Dumais , John Platt , David Heckerman , Mehran Sahami, Inductive learning algorithms and representations for text categorization, Proceedings of the seventh international conference on Information and knowledge management, p.148-155, November 02-07, 1998, Bethesda, Maryland, United States [doi>10.1145/288627.288651]
• 14: Excite. http://www.excite.com/
• 15: Google. http:l/www.google.coml
• 16: E. Horvitz, J. Breese, D. Heckerman, D. Hovel, and K. Rommelse. The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users. In Proceedings of the Fourteenth Conference on Uncertainty in Arttjicial Intelligence. AAAI Press, 1998.
• 17: Tessa Lau , Eric Horvitz, Patterns of search: analyzing and modeling Web query refinement, Proceedings of the seventh international conference on User modeling, p.119-128, June 1999, Banff, Canada
• 18: D. Heckerman and E. Horvitz. Inferring Informational Goals from Free-Text Queries. In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence. AAAI Press, 1998.
• 19: Lycos. http://www.lycos.comf
• 20: Michel Jaczynski , Brigitte Trousse, WWW Assisted Browsing by Reusing Past Navigations of a Group of Users, Proceedings of the 4th European Workshop on Advances in Case-Based Reasoning, p.160-171, September 01, 1998
• 21: Jansen, B., Spink, A., and Bateman, J. Searchers, the Subjects they Search, and Sufficiency: A Study of a Large Sample of EXCITE Searches. In Proceedings of WebNet-98, World Conference of the Www, Internet and Intranet. AACE Press, 1998.
• 22: Christopher Johnson , Larry Birnbaum , Ray Bareiss , Tom Hinrichs, Integrating organizational memory and performance support, Proceedings of the 4th international conference on Intelligent user interfaces, p.127-134, January 05-08, 1999, Los Angeles, California, United States [doi>10.1145/291080.291102]
• 23: Joachims, T., Freitag, D., and Mitchell, T. WebWatcher: A Tour Guide for the World Wide Web. In Proceedings of the Fourteenth National Conference on Artificial Intelligence. AAAI Press, 1996.
• 24: Lieberman, H. (1995). Letizia: An Agent That Assists Web Browsing. In Proceedings of IJCAI-95, International Joint Conference on Artificial Intelligence. July 1995.
• 25: Pazzani, M., Muramatsu J., & Billsus, D. Syskill & Webert: Identifying interesting web sites. Proceedings of the Fourteenth National Conference on Artificial Intelligence. AAAI Press, 1996.
• 26: Rhodes, B., and Starner, T. A continuously running automated information retrieval system. In Proceedings of The First International Conference on The Practical Application of Intelligent Agents and Multi Agent Technology. April 1996.
• 27: Riesbeck, C. What Next? The Future of Case-based reasoning in Post-Modem AI. In Leake, ed., Case- Based Reasoning: Experiences, Lessons, and Future Directions. New York, NY: AAAIIMIT Press, 1996.
• 28: Gerard Salton , Chris Buckley, Improving retrieval performance by relevance feedback, Readings in information retrieval, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1997
• 29: G. Salton , A. Wong , C. S. Yang, A vector space model for automatic indexing, Communications of the ACM, v.18 n.11, p.613-620, Nov. 1975 [doi>10.1145/361219.361220]
• 30: Ellen Spertus, ParaSite: mining structural information on the Web, Selected papers from the sixth international conference on World Wide Web, p.1205-1215, September 1997, Santa Clara, California, United States
• 31: Spink, A., Bateman, J., and Jansen, B. Users' Searching Behavior on the EXCITE Web Search Engine. In Proceedings of WebNet-98, World Conference of the WWW Internet and Intranet. AACE Press, 1998.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)

General Terms:
Design, Experimentation, Human Factors

Keywords:
context, information agent, intelligent information access, resource discovery