TY - JOUR
T1 - Supporting non-English Web searching
T2 - An experiment on the Spanish business and the Arabic medical intelligence portals
AU - Chung, Wingyan
AU - Bonillas, Alfonso
AU - Lai, Guanpi
AU - Xi, Wei
AU - Chen, Hsinchun
N1 - Funding Information:
This research was partly supported by funding from the National Science Foundation Knowledge Discovery and Dissemination (KDD) program #9983304, June 2003–March 2004 and October 2003–March 2004 and from the University Research Institute Grant Program of the University of Texas at El Paso. We are grateful to our project members and the experts and the student subjects who participated in the user study.
PY - 2006/12
Y1 - 2006/12
N2 - Although non-English-speaking online populations are growing rapidly, support for searching non-English Web content is much weaker than for English content. Prior research has implicitly assumed English to be the primary language used on the Web, but this is not the case for many non-English-speaking regions. This research proposes a language-independent approach that uses meta-searching, statistical language processing, summarization, categorization, and visualization techniques to build high-quality domain-specific collections and to support searching and browsing of non-English information. Based on this approach, we developed SBizPort and AMedPort for the Spanish business and Arabic medical domains respectively. Experimental results showed that the portals achieved significantly better search accuracy, information quality, and overall satisfaction than benchmark search engines. Subjects strongly favored the portals' search and browse functionality and user interface. This research thus contributes to developing and validating a useful approach to non-English Web searching and providing an example of supporting decision-making in non-English Web domains.
AB - Although non-English-speaking online populations are growing rapidly, support for searching non-English Web content is much weaker than for English content. Prior research has implicitly assumed English to be the primary language used on the Web, but this is not the case for many non-English-speaking regions. This research proposes a language-independent approach that uses meta-searching, statistical language processing, summarization, categorization, and visualization techniques to build high-quality domain-specific collections and to support searching and browsing of non-English information. Based on this approach, we developed SBizPort and AMedPort for the Spanish business and Arabic medical domains respectively. Experimental results showed that the portals achieved significantly better search accuracy, information quality, and overall satisfaction than benchmark search engines. Subjects strongly favored the portals' search and browse functionality and user interface. This research thus contributes to developing and validating a useful approach to non-English Web searching and providing an example of supporting decision-making in non-English Web domains.
KW - Arabic
KW - Browsing
KW - Business intelligence
KW - Categorization
KW - Internet
KW - Kohonen self-organizing map
KW - Medical intelligence
KW - Mutual information
KW - Non-English Web searching
KW - Searching
KW - Spanish
KW - Summarization
KW - Visualization
KW - Web
KW - Web portal
UR - http://www.scopus.com/inward/record.url?scp=33750456989&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33750456989&partnerID=8YFLogxK
U2 - 10.1016/j.dss.2006.02.015
DO - 10.1016/j.dss.2006.02.015
M3 - Article
AN - SCOPUS:33750456989
SN - 0167-9236
VL - 42
SP - 1697
EP - 1714
JO - Decision Support Systems
JF - Decision Support Systems
IS - 3
ER -