Comparing explicit and implicit feedback techniques for web retrieval: TREC-10 interactive track report

R.W. White, J.M. Jose, I. Ruthven, E.M. Voorhees (Editor), D.K. Harman (Editor)

Research output: Contribution to conferencePaper

Abstract

In this paper we examine the extent to which implicit feedback (where the system attempts to estimate what the user may be interested in) can act as a substitute for explicit feedback (where searchers explicitly mark documents relevant). Therefore, we attempt to side-step the problem of getting users to explicitly mark documents relevant by making predictions on relevance through analysing the user's interaction with the system. Specifically, we hypothesised that implicit and explicit feedback were interchangeable as sources of relevance information for relevance feedback. Through developing a system that utilised each type of feedback we were able to compare the two approaches in terms of search effectiveness.
LanguageEnglish
Pages534-538
Number of pages5
Publication statusPublished - 12 Feb 2002
EventProceedings of the Tenth Text Retrieval Conference (TREC-10) - Maryland, USA
Duration: 13 Nov 200116 Nov 2001

Conference

ConferenceProceedings of the Tenth Text Retrieval Conference (TREC-10)
CityMaryland, USA
Period13/11/0116/11/01

Fingerprint

Feedback

Keywords

  • explicit feedback
  • implicit feedback
  • web retrieval
  • searching

Cite this

White, R. W., Jose, J. M., Ruthven, I., Voorhees, E. M. (Ed.), & Harman, D. K. (Ed.) (2002). Comparing explicit and implicit feedback techniques for web retrieval: TREC-10 interactive track report. 534-538. Paper presented at Proceedings of the Tenth Text Retrieval Conference (TREC-10), Maryland, USA, .
White, R.W. ; Jose, J.M. ; Ruthven, I. ; Voorhees, E.M. (Editor) ; Harman, D.K. (Editor). / Comparing explicit and implicit feedback techniques for web retrieval : TREC-10 interactive track report. Paper presented at Proceedings of the Tenth Text Retrieval Conference (TREC-10), Maryland, USA, .5 p.
@conference{368416c25a9b48ba8c012fd9d84c19fd,
title = "Comparing explicit and implicit feedback techniques for web retrieval: TREC-10 interactive track report",
abstract = "In this paper we examine the extent to which implicit feedback (where the system attempts to estimate what the user may be interested in) can act as a substitute for explicit feedback (where searchers explicitly mark documents relevant). Therefore, we attempt to side-step the problem of getting users to explicitly mark documents relevant by making predictions on relevance through analysing the user's interaction with the system. Specifically, we hypothesised that implicit and explicit feedback were interchangeable as sources of relevance information for relevance feedback. Through developing a system that utilised each type of feedback we were able to compare the two approaches in terms of search effectiveness.",
keywords = "explicit feedback, implicit feedback, web retrieval, searching",
author = "R.W. White and J.M. Jose and I. Ruthven and E.M. Voorhees and D.K. Harman",
year = "2002",
month = "2",
day = "12",
language = "English",
pages = "534--538",
note = "Proceedings of the Tenth Text Retrieval Conference (TREC-10) ; Conference date: 13-11-2001 Through 16-11-2001",

}

White, RW, Jose, JM, Ruthven, I, Voorhees, EM (ed.) & Harman, DK (ed.) 2002, 'Comparing explicit and implicit feedback techniques for web retrieval: TREC-10 interactive track report' Paper presented at Proceedings of the Tenth Text Retrieval Conference (TREC-10), Maryland, USA, 13/11/01 - 16/11/01, pp. 534-538.

Comparing explicit and implicit feedback techniques for web retrieval : TREC-10 interactive track report. / White, R.W.; Jose, J.M.; Ruthven, I.; Voorhees, E.M. (Editor); Harman, D.K. (Editor).

2002. 534-538 Paper presented at Proceedings of the Tenth Text Retrieval Conference (TREC-10), Maryland, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Comparing explicit and implicit feedback techniques for web retrieval

T2 - TREC-10 interactive track report

AU - White, R.W.

AU - Jose, J.M.

AU - Ruthven, I.

A2 - Voorhees, E.M.

A2 - Harman, D.K.

PY - 2002/2/12

Y1 - 2002/2/12

N2 - In this paper we examine the extent to which implicit feedback (where the system attempts to estimate what the user may be interested in) can act as a substitute for explicit feedback (where searchers explicitly mark documents relevant). Therefore, we attempt to side-step the problem of getting users to explicitly mark documents relevant by making predictions on relevance through analysing the user's interaction with the system. Specifically, we hypothesised that implicit and explicit feedback were interchangeable as sources of relevance information for relevance feedback. Through developing a system that utilised each type of feedback we were able to compare the two approaches in terms of search effectiveness.

AB - In this paper we examine the extent to which implicit feedback (where the system attempts to estimate what the user may be interested in) can act as a substitute for explicit feedback (where searchers explicitly mark documents relevant). Therefore, we attempt to side-step the problem of getting users to explicitly mark documents relevant by making predictions on relevance through analysing the user's interaction with the system. Specifically, we hypothesised that implicit and explicit feedback were interchangeable as sources of relevance information for relevance feedback. Through developing a system that utilised each type of feedback we were able to compare the two approaches in terms of search effectiveness.

KW - explicit feedback

KW - implicit feedback

KW - web retrieval

KW - searching

UR - http://trec.nist.gov/pubs/trec10/papers/glasgow.pdf

UR - http://www.cis.strath.ac.uk/research/publications/papers/strath_cis_publication_145.pdf

M3 - Paper

SP - 534

EP - 538

ER -

White RW, Jose JM, Ruthven I, Voorhees EM, (ed.), Harman DK, (ed.). Comparing explicit and implicit feedback techniques for web retrieval: TREC-10 interactive track report. 2002. Paper presented at Proceedings of the Tenth Text Retrieval Conference (TREC-10), Maryland, USA, .