An Approach For Evaluation Of Semantic Performance Of Search Engines: Google, Yahoo, Msn And Hakia
Author(s) -
Marwan S. M. Aldabbagh
Publication year - 2012
Publication title -
mağallaẗ al-tarbiyaẗ wa-al-ʻilm
Language(s) - English
Resource type - Journals
eISSN - 2664-2530
pISSN - 1812-125X
DOI - 10.33899/edusj.2012.66950
Subject(s) - computer science , information retrieval , phrase , search engine , set (abstract data type) , syntax , phrase search , web search query , world wide web , natural language processing , web query classification , programming language
Ten queries of different subjects were run over yahoo, Google, Msn and Hakia search engines. Second set of experiment comprise four phrases of the same meaning but different syntax were attached to each query and the combinations were run over Hakia search engine. Four thousand retrieved documents were classified as relevant, duplicate different source, non – relevant, duplicate same source and inaccessible An Approach For Evaluation Of Semantic Performance Of Search Engines ... 125 documents. Calculation of relative precision of the two sets of data, show maximum relative precision for Hakia search engine followed by exchange places search engines of Yahoo and Google, where the lowest relevant precision is shown by Msn. For the second set of data, phrase “information about“ with query shown maximum relevant precision followed by phrase “what is“ where as phrase “description of“ and “definition“ show lowest relevant precision. Comparison of web document retrieval performance were accounted for in the discussion.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom