Evaluating Google queries based on language preferences

被引:12
作者
Al-Eroud, Ahmed F. [1 ]
Al-Ramahi, Mohammad A. [1 ]
Al-Kabi, Mohammed N. [1 ]
Alsmadi, Izzat M. [1 ]
Al-Shawakfa, Emad M. [1 ]
机构
[1] Yarmouk Univ, Dept Comp Informat Syst, Fac Informat Technol & Comp Sci, Irbid 21163, Jordan
关键词
Cross-Lingual Information Retrieval (CLIR); information retrieval; page ranking; query processing and indexing; search engines; RETRIEVAL; INFORMATION;
D O I
10.1177/0165551511403383
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper evaluates the assumption that users expect search engines to retrieve the same results for queries regardless of the language or the location of the originator. The dependency of the Google search engine on the language and location from which the query is submitted has been evaluated. The most popular queries in Arabic language were selected and translated into English for comparison using the Google translator. When studying keyword traffic on both Google search based keyword tool and Google Insights for Search, results showed that 67% of the Arab Internet users prefer to use English queries instead of their Arabic counterpart. When studying Google responses to some popular queries we have found that Google ranking algorithm depends on the language of the query more than on the keyword popularity. Although results justify search engines' favouritism of giving documents in English priority over those of other languages, nonetheless, future search engine indexers should separate the document language from its content in a structure that makes the language a pluggable attribute for those indexed documents.
引用
收藏
页码:282 / 292
页数:11
相关论文
共 20 条
[11]   Using EuroWordNet in a concept-based approach to cross-language text retrieval [J].
Gonzalo, J ;
Verdejo, F ;
Chugur, I .
APPLIED ARTIFICIAL INTELLIGENCE, 1999, 13 (07) :647-678
[12]  
HERMES R, 2006, J AM SOC INFORM SCI, V57, P501
[13]  
HUANG C, 2001, P 10 WWW C 10 WWW C
[14]  
JANEVSKI I, 2008, INNOVATIONS INFORM T
[15]  
Ko J., 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, P784
[16]   Implicit ambiguity resolution using incremental clustering in cross-language information retrieval [J].
Lee, KS ;
Kageura, K ;
Choi, KS .
INFORMATION PROCESSING & MANAGEMENT, 2004, 40 (01) :145-159
[17]  
MOUKDAD H, 2004, ACCESS INFORM TECHNO
[18]   Language preferences on websites and in google searches for human health and food information [J].
Singh, Punam Mony ;
Wight, Carly A. ;
Sercinoglu, Olcan ;
Wilson, David C. ;
Boytsov, Artem ;
Raizada, Manish N. .
JOURNAL OF MEDICAL INTERNET RESEARCH, 2007, 9 (02) :e18
[19]  
XINHUI T, 2008, INT C NAT LANG PROC, V4, P1
[20]   Multi-Language Ontology-based Search Engine [J].
Zhuhadar, Leyla ;
Nasraoui, Olfa ;
Wyatt, Robert ;
Romero, Elizabeth .
THIRD INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER-HUMAN INTERACTIONS: ACHI 2010, 2010, :13-18