Measuring recall

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Recall, the proportion of the relevant documents that is retrieved, is a key indicator of the performance of an information retrieval system. With large information systems, like the World Wide Web on the Internet, recall is almost impossible to measure or estimate by all standard techniques. A proposal 'needle hiding' is made as a technique to estimate recall. It is also shown that ranking by relative recall does not have to be isomorphic to ranking by recall; hence the use of relative recall for comparative evaluation might not be entirely sound.

Original languageEnglish (US)
Pages (from-to)409-417
Number of pages9
JournalJournal of Information Science
Volume24
Issue number6
StatePublished - 1998

Fingerprint

Information retrieval systems
World Wide Web
Needles
ranking
Information systems
Acoustic waves
Internet
information retrieval
information system
evaluation
performance

ASJC Scopus subject areas

  • Information Systems
  • Library and Information Sciences

Cite this

Measuring recall. / Fricke, Martin H.

In: Journal of Information Science, Vol. 24, No. 6, 1998, p. 409-417.

Research output: Contribution to journalArticle

Fricke, MH 1998, 'Measuring recall', Journal of Information Science, vol. 24, no. 6, pp. 409-417.
Fricke, Martin H. / Measuring recall. In: Journal of Information Science. 1998 ; Vol. 24, No. 6. pp. 409-417.
@article{d9b282623af540f598acf518b4c4c64a,
title = "Measuring recall",
abstract = "Recall, the proportion of the relevant documents that is retrieved, is a key indicator of the performance of an information retrieval system. With large information systems, like the World Wide Web on the Internet, recall is almost impossible to measure or estimate by all standard techniques. A proposal 'needle hiding' is made as a technique to estimate recall. It is also shown that ranking by relative recall does not have to be isomorphic to ranking by recall; hence the use of relative recall for comparative evaluation might not be entirely sound.",
author = "Fricke, {Martin H}",
year = "1998",
language = "English (US)",
volume = "24",
pages = "409--417",
journal = "Journal of Information Science",
issn = "0165-5515",
publisher = "SAGE Publications Ltd",
number = "6",

}

TY - JOUR

T1 - Measuring recall

AU - Fricke, Martin H

PY - 1998

Y1 - 1998

N2 - Recall, the proportion of the relevant documents that is retrieved, is a key indicator of the performance of an information retrieval system. With large information systems, like the World Wide Web on the Internet, recall is almost impossible to measure or estimate by all standard techniques. A proposal 'needle hiding' is made as a technique to estimate recall. It is also shown that ranking by relative recall does not have to be isomorphic to ranking by recall; hence the use of relative recall for comparative evaluation might not be entirely sound.

AB - Recall, the proportion of the relevant documents that is retrieved, is a key indicator of the performance of an information retrieval system. With large information systems, like the World Wide Web on the Internet, recall is almost impossible to measure or estimate by all standard techniques. A proposal 'needle hiding' is made as a technique to estimate recall. It is also shown that ranking by relative recall does not have to be isomorphic to ranking by recall; hence the use of relative recall for comparative evaluation might not be entirely sound.

UR - http://www.scopus.com/inward/record.url?scp=0032303052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032303052&partnerID=8YFLogxK

M3 - Article

VL - 24

SP - 409

EP - 417

JO - Journal of Information Science

JF - Journal of Information Science

SN - 0165-5515

IS - 6

ER -