Knowledge-based navigation of complex information spaces

  • Authors:
  • Robin D. Burke;Kristian J. Hammond;Benjamin C. Young

  • Affiliations:
  • Artificial Intelligence Laboratory, University of Chicago, Chicago, IL;Artificial Intelligence Laboratory, University of Chicago, Chicago, IL;Artificial Intelligence Laboratory, University of Chicago, Chicago, IL

  • Venue:
  • AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

While the explosion of on-line information has brought new opportunities for finding and using electronic data, it has also brought to the forefront the problem of isolating useful information and making sense of large multidimension information spaces. We have built several developed an approach to building data "tour guides," called FINDME systems. These programs know enough about an information space to be able to help a user navigate through it. The user not only comes away with items of useful information but also insights into the structure of the information space itself. In these systems, we have combined ideas of instance-based browsing, structuring retrieval around the critiquing of previously-retrieved examples, and retrieval strategies, knowledge-based heuristics for finding relevant information. We illustrate these techniques with several examples, concentrating especially on the RENTME system, a FINDME system for helping users find suitable rental apartments in the Chicago metropolitan area.