Evaluating the summarization algorithms of Ask.com, Bing, Google and Yahoo: search snippets-result conformance.

Purpose: Objective: The objective of the research was to evaluate the performance of the summarization algorithms utilized by Ask.com, Bing, Google and Yahoo. Design/methodology/approach: This study evaluated the summarization algorithms employed by search engines. In this regard, a set of 30 search...

Descripción completa

Detalles Bibliográficos
Publicado en:Performance Measurement & Metrics Vol. 26; no. 4; pp. 233 - 253
Autores principales: Zeynali-Tazehkandi, Mahdi, Nowkarizi, Mohsen, Zhian-Feizabadi, Yeganeh
Formato: pictorial research tables/charts Journal Article
Publicado: Emerald Publishing Limited 2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=188908250&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 188908250
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        14678047
        NG6
      jtl: Performance Measurement & Metrics
      issn: 14678047
      maglogo: N
    pubinfo:
      dt: 2025
      vid: 26
      iid: 4
      pid: 465
      pub: Emerald Publishing Limited
    artinfo:
      ui:
        188908250
        188908250
        188908250
        10.1108/PMM-02-2024-0012
        188908250
      ppf: 233
      ppct: 20
      formats:
      tig:
        atl: Evaluating the summarization algorithms of Ask.com, Bing, Google and Yahoo: search snippets-result conformance.
      aug:
        au:
          Zeynali-Tazehkandi, Mahdi
          Nowkarizi, Mohsen
          Zhian-Feizabadi, Yeganeh
        affil: Ferdowsi University of Mashhad, Mashhad, Iran
      sug:
        subj:
          Information Storage
          Information Retrieval
          Algorithms Evaluation
          Internet Searching Methods
          Web Search Engines
          Human
          Iran
          Evaluation Research
          Stratified Random Sample
          Questionnaires
          Summated Rating Scaling
          Nonparametric Statistics
          Friedman Test
          Data Analysis Software
          Ontologies
          World Wide Web
          Abstracts
      ab: Purpose: Objective: The objective of the research was to evaluate the performance of the summarization algorithms utilized by Ask.com, Bing, Google and Yahoo. Design/methodology/approach: This study evaluated the summarization algorithms employed by search engines. In this regard, a set of 30 search terms was carefully constructed using schema ontology. These terms were subsequently employed to interrogate the selected search engines. A random selection of three results from each set of ten retrieved results was then extracted for thorough evaluation. The evaluation process involved quantifying the degree of relevance deviation between the search snippets and the corresponding full-text results. This analysis served to effectively measure the effectiveness of the search engines' summarization algorithms. Findings: The research findings indicated a substantial discrepancy between the relevance of search snippets and the corresponding full-text search results. Furthermore, the findings underscored notable differences among the summarization algorithms utilized by Ask.com, Bing, Google and Yahoo. Additionally, the study found that the abstracting quality of Ask.com, Bing, Google and Yahoo was 43.4, 57.2, 51.8 and 47.8%, respectively. Practical implications: Users are recommended to employ Bing and Google for conducting search queries. The developers of Ask.com and Yahoo are urged to refine their summarization algorithms. Originality/value: This study constitutes the first-ever attempt to assess the summarization capabilities of Ask.com, Bing, Google and Yahoo.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N