Using top-ranking sentences to facilitate effective information access

R.W. White, J.M. Jose, I. Ruthven

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Web searchers typically fail to view search results beyond the first page nor fully examine those results presented to them. In this article we describe an approach that encourages a deeper examination of the contents of the document set retrieved in response to a searcher's query. The approach shifts the focus of perusal and interaction away from potentially uninformative document surrogates (such as titles, sentence fragments, and URLs) to actual document content, and uses this content to drive the information seeking process. Current search interfaces assume searchers examine results document-by-document. In contrast our approach extracts, ranks, and presents the contents of the top-ranked document set. We use query-relevant top-ranking sentences extracted from the top documents at retrieval time as fine-grained representations of top-ranked document content and, when combined in a ranked list, an overview of these documents. The interaction of the searcher provides implicit evidence that is used to reorder the sentences where appropriate. We evaluate our approach in three separate user studies, each applying these sentences in a different way. The findings of these studies show that top-ranking sentences can facilitate effective information access.
LanguageEnglish
Pages1113-1125
Number of pages12
JournalJournal of the American Society for Information Science and Technology
Volume56
Issue number10
DOIs
Publication statusPublished - 2005

Fingerprint

Websites

Keywords

  • top-ranking sentences
  • content-driven information seeking
  • user studies
  • implicit feedback
  • searching
  • information retrieval

Cite this

@article{4f5f0a1630b747259ca17c4259548893,
title = "Using top-ranking sentences to facilitate effective information access",
abstract = "Web searchers typically fail to view search results beyond the first page nor fully examine those results presented to them. In this article we describe an approach that encourages a deeper examination of the contents of the document set retrieved in response to a searcher's query. The approach shifts the focus of perusal and interaction away from potentially uninformative document surrogates (such as titles, sentence fragments, and URLs) to actual document content, and uses this content to drive the information seeking process. Current search interfaces assume searchers examine results document-by-document. In contrast our approach extracts, ranks, and presents the contents of the top-ranked document set. We use query-relevant top-ranking sentences extracted from the top documents at retrieval time as fine-grained representations of top-ranked document content and, when combined in a ranked list, an overview of these documents. The interaction of the searcher provides implicit evidence that is used to reorder the sentences where appropriate. We evaluate our approach in three separate user studies, each applying these sentences in a different way. The findings of these studies show that top-ranking sentences can facilitate effective information access.",
keywords = "top-ranking sentences, content-driven information seeking, user studies, implicit feedback, searching, information retrieval",
author = "R.W. White and J.M. Jose and I. Ruthven",
year = "2005",
doi = "10.1002/asi.20203",
language = "English",
volume = "56",
pages = "1113--1125",
journal = "Journal of the American Society for Information Science and Technology",
issn = "1532-2890",
number = "10",

}

Using top-ranking sentences to facilitate effective information access. / White, R.W.; Jose, J.M.; Ruthven, I.

In: Journal of the American Society for Information Science and Technology, Vol. 56, No. 10, 2005, p. 1113-1125.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using top-ranking sentences to facilitate effective information access

AU - White, R.W.

AU - Jose, J.M.

AU - Ruthven, I.

PY - 2005

Y1 - 2005

N2 - Web searchers typically fail to view search results beyond the first page nor fully examine those results presented to them. In this article we describe an approach that encourages a deeper examination of the contents of the document set retrieved in response to a searcher's query. The approach shifts the focus of perusal and interaction away from potentially uninformative document surrogates (such as titles, sentence fragments, and URLs) to actual document content, and uses this content to drive the information seeking process. Current search interfaces assume searchers examine results document-by-document. In contrast our approach extracts, ranks, and presents the contents of the top-ranked document set. We use query-relevant top-ranking sentences extracted from the top documents at retrieval time as fine-grained representations of top-ranked document content and, when combined in a ranked list, an overview of these documents. The interaction of the searcher provides implicit evidence that is used to reorder the sentences where appropriate. We evaluate our approach in three separate user studies, each applying these sentences in a different way. The findings of these studies show that top-ranking sentences can facilitate effective information access.

AB - Web searchers typically fail to view search results beyond the first page nor fully examine those results presented to them. In this article we describe an approach that encourages a deeper examination of the contents of the document set retrieved in response to a searcher's query. The approach shifts the focus of perusal and interaction away from potentially uninformative document surrogates (such as titles, sentence fragments, and URLs) to actual document content, and uses this content to drive the information seeking process. Current search interfaces assume searchers examine results document-by-document. In contrast our approach extracts, ranks, and presents the contents of the top-ranked document set. We use query-relevant top-ranking sentences extracted from the top documents at retrieval time as fine-grained representations of top-ranked document content and, when combined in a ranked list, an overview of these documents. The interaction of the searcher provides implicit evidence that is used to reorder the sentences where appropriate. We evaluate our approach in three separate user studies, each applying these sentences in a different way. The findings of these studies show that top-ranking sentences can facilitate effective information access.

KW - top-ranking sentences

KW - content-driven information seeking

KW - user studies

KW - implicit feedback

KW - searching

KW - information retrieval

UR - http://www.asis.org/Publications/JASIS/jasis.html

UR - http://dx.doi.org/10.1002/asi.20203

UR - http://www.cis.strath.ac.uk/research/publications/papers/strath_cis_publication_515.pdf

U2 - 10.1002/asi.20203

DO - 10.1002/asi.20203

M3 - Article

VL - 56

SP - 1113

EP - 1125

JO - Journal of the American Society for Information Science and Technology

T2 - Journal of the American Society for Information Science and Technology

JF - Journal of the American Society for Information Science and Technology

SN - 1532-2890

IS - 10

ER -