Reducing Indeterminism In Consultation: A Cognitive Model of User/Librarian Interactions

Persistent Link:
http://hdl.handle.net/10150/106096
Title:
Reducing Indeterminism In Consultation: A Cognitive Model of User/Librarian Interactions
Author:
Chen, Hsinchun; Dhar, Vasant
Citation:
Reducing Indeterminism In Consultation: A Cognitive Model of User/Librarian Interactions 1987,
Publisher:
AAAI
Issue Date:
1987
Description:
Artificial Intelligence Lab, Department of MIS, University of Arizona
URI:
http://hdl.handle.net/10150/106096
Submitted date:
2004-09-20
Abstract:
In information facilities such as libraries, finding documents that are relevant to a user query is difficult because of the indeterminism involved in the process by which documents are indexed, and the latitude users have in choosing terms to express a query on a particular topic. Reference librarians play an important support role in coping with this indeterminism, focusing user queries through an interactive dialog. Based on thirty detailed observations of user/librarian interactions obtained through a field experiment, we have developed a computational model designed to simulate the reference librarian. The consultation includes two phases. The first is handle search, where the userâ s rough problem statement and a user stereotyping imposed by the librarian are used in determining the appropriate tools (handles). The second phase is document search, involving the search for documents within a chosen handle. We are collaborating with the university library for putting our model to use as an intelligent assistant for an online retrieval system.
Type:
Conference Paper
Language:
en
Keywords:
Libraries; Information Seeking Behaviors; Reference Services
Local subject classification:
National Science Digital Library; NSDL; Artificial Intelligence lab; AI lab; University libraries

Full metadata record

DC FieldValue Language
dc.contributor.authorChen, Hsinchunen_US
dc.contributor.authorDhar, Vasanten_US
dc.date.accessioned2004-09-20T00:00:01Z-
dc.date.available2010-06-18T23:39:38Z-
dc.date.issued1987en_US
dc.date.submitted2004-09-20en_US
dc.identifier.citationReducing Indeterminism In Consultation: A Cognitive Model of User/Librarian Interactions 1987,en_US
dc.identifier.urihttp://hdl.handle.net/10150/106096-
dc.descriptionArtificial Intelligence Lab, Department of MIS, University of Arizonaen_US
dc.description.abstractIn information facilities such as libraries, finding documents that are relevant to a user query is difficult because of the indeterminism involved in the process by which documents are indexed, and the latitude users have in choosing terms to express a query on a particular topic. Reference librarians play an important support role in coping with this indeterminism, focusing user queries through an interactive dialog. Based on thirty detailed observations of user/librarian interactions obtained through a field experiment, we have developed a computational model designed to simulate the reference librarian. The consultation includes two phases. The first is handle search, where the userâ s rough problem statement and a user stereotyping imposed by the librarian are used in determining the appropriate tools (handles). The second phase is document search, involving the search for documents within a chosen handle. We are collaborating with the university library for putting our model to use as an intelligent assistant for an online retrieval system.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoenen_US
dc.publisherAAAIen_US
dc.subjectLibrariesen_US
dc.subjectInformation Seeking Behaviorsen_US
dc.subjectReference Servicesen_US
dc.subject.otherNational Science Digital Libraryen_US
dc.subject.otherNSDLen_US
dc.subject.otherArtificial Intelligence laben_US
dc.subject.otherAI laben_US
dc.subject.otherUniversity librariesen_US
dc.titleReducing Indeterminism In Consultation: A Cognitive Model of User/Librarian Interactionsen_US
dc.typeConference Paperen_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.