Indexing stories as social advice

  • Authors:
  • Eric A. Domeshek

  • Affiliations:
  • Institute for the Learning Sciences, Northwestern University, Evanston, Illinois

  • Venue:
  • AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 1
  • Year:
  • 1991

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper reports on an indexing system supporting retrieval of past cases as advice about everyday social problems; it has been implemented in the Abby lovelorn advising system. Two points are emphasized: (1) indices are descriptions of problems and their causes, couched in a vocabulary centered on intentional causality, and (2) indices fit a fixed format that allows reification of identity and thematic relationships as features. Abby answers several of the central questions that any indexing system must address, and has advantages over less restrictive systems.