TY - GEN
T1 - A methodology to find web site keywords
AU - Velásquez, Juan D.
AU - Weber, Richard
AU - Yasuda, Hiroshi
AU - Aoki, Terumasa
PY - 2004
Y1 - 2004
N2 - For many companies and/or institutions it is no longer sufficient to have a web site and high quality products or services. What in many cases makes the difference between success and failure of e-business is the potential of the respective web site to attract and retain visitors. This potential is determined by a site's content, its design, and technical aspects, such as e.g. time to load the pages among others. In this paper, we concentrate on the content represented by free text of each of the web pages. We propose a method to determine the set of the most important words in a web site from the visitor's point of view. This is done combining usage information with web page content arriving at a set of keywords determined implicitly by the site's visitors. Applying self-organizing neural networks to the respective usage and content data we can identify clusters of typical visitors and the most important pages and words for each cluster. We applied our method to a bank's web site in order to show its benefits. Institutions that perform consequently and regularly the proposed analysis can design their web sites according to their visitors' needs and requirements and this way stay ahead of their competitors.
AB - For many companies and/or institutions it is no longer sufficient to have a web site and high quality products or services. What in many cases makes the difference between success and failure of e-business is the potential of the respective web site to attract and retain visitors. This potential is determined by a site's content, its design, and technical aspects, such as e.g. time to load the pages among others. In this paper, we concentrate on the content represented by free text of each of the web pages. We propose a method to determine the set of the most important words in a web site from the visitor's point of view. This is done combining usage information with web page content arriving at a set of keywords determined implicitly by the site's visitors. Applying self-organizing neural networks to the respective usage and content data we can identify clusters of typical visitors and the most important pages and words for each cluster. We applied our method to a bank's web site in order to show its benefits. Institutions that perform consequently and regularly the proposed analysis can design their web sites according to their visitors' needs and requirements and this way stay ahead of their competitors.
UR - http://www.scopus.com/inward/record.url?scp=4544370840&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=4544370840&partnerID=8YFLogxK
U2 - 10.1109/eee.2004.1287324
DO - 10.1109/eee.2004.1287324
M3 - Conference contribution
AN - SCOPUS:4544370840
SN - 0769520731
SN - 9780769520735
T3 - Proceedings - 2004 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE 2004
SP - 285
EP - 292
BT - Proceedings - 2004 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE 2004
PB - IEEE Computer Society
T2 - Proceedings - 2004 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE 2004
Y2 - 28 March 2004 through 31 March 2004
ER -