Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Query expansion med hjälp av en elektronisk tesaurus i en bibliografisk online-databas.
University of Borås, Swedish School of Library and Information Science.
University of Borås, Swedish School of Library and Information Science.
2003 (Swedish)Independent thesis Advanced level (degree of Master (One Year))Student thesisAlternative title
Query expansion using an electronic thesaurus in a bibliographic online database. (English)
Abstract [en]

In this Masters thesis we investigate query expansion using an electronic thesaurus. We formed 30 topics from the library and information science field. For each topic three searches were made in the bibliographic database LISA Library and Information Science Abstracts via CSA Cambridge Scientific Abstracts. LISA has an electronic thesaurus attached. We used this thesaurus to form baseline queries, baseline queries expanded with synonyms, and baseline queries expanded with both synonyms and related terms. The terms used in the baseline queries were the terms preferred by the thesaurus the "use for" terms. The three query types were analyzed with regard to precision and relative recall. The relative recall was set to 100% for the strategy where a baseline query was expanded with both synonyms and related terms. The average precision for the searches using baseline queries was 41% with a 60% relative recall. For the searches using baseline queries expanded with synonyms, the precision was 39% and the relative recall was 72%. The searches using baseline queries expanded with both synonyms and related terms resulted in an average precision of 37%. We also measured the "net effect", that is, the precision and recall with regard to the new documents retrieved by each search strategy. We found that, on average, 60% of the relevant documents were retrieved by the baseline queries. The strategy using a baseline query expanded with synonyms was the least effective one in retrieving new relevant documents on average it brought only 12% of the relevant documents. When measuring the precision for the new documents retrieved by each search strategy we encountered a methodological problem which is discussed in this thesis.

Place, publisher, year, edition, pages
University College of Borås. Swedish School of Library and Information Science (SSLIS) , 2003.
Series
Magisteruppsats i biblioteks- och informationsvetenskap vid Bibliotekshögskolan/Biblioteks- och informationsvetenskap, ISSN 1404-0891 ; 2003:49
Keywords [en]
library and information science
Keywords [sv]
biblioteks- och informationsvetenskap
National Category
Social Sciences
Identifiers
URN: urn:nbn:se:hb:diva-20957Local ID: 2320/965OAI: oai:DiVA.org:hb-20957DiVA, id: diva2:1312891
Note
Uppsatsnivå: DAvailable from: 2019-04-30 Created: 2019-04-30

Open Access in DiVA

fulltext(124 kB)2 downloads
File information
File name FULLTEXT01.pdfFile size 124 kBChecksum SHA-512
70db2bbe43bbfcb2617b19e2e6c730acba3ff198a310144469674f07ce5f94964315d523f0a06c7edc1daf24b8412316a0790d99431c38ef1e0c588be2b14ebe
Type fulltextMimetype application/pdf

By organisation
Swedish School of Library and Information Science
Social Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 2 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 13 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf