Applying Web Mining Techniques for Constructing Webometrics Ranking early Warning System

Abstract

The management of university web sites is becoming more critical than before due to the rapid growth of the population dependent on the world wide web as the most important (if not the only) information source. A university can spread its research outcomes and education achievements through its web site, and consequently gain visibility and influence from the web population. Webometrics Ranking of World Universities (WR) proposed by Centre for Scientific Information and Documentation (CINDOC-CSIC), which ranks the university web sites, has obtained much attention recently. The rankings of WR are well recognized as an important index for universities willing to promote themselves by the internet technology. In this paper, we proposed WRES as an early warning system for Webometrics Rankings. WRES gathers the WR indices from the WWW automatically in flexible periods, and provides useful information in real time for the managers of university web sites. If the WR ranking of an institution is below the expected position according to their academic performance, university authorities should reconsider their web policy, by promoting substantial increases of the volume and quality of their electronic publications. Besides, the web site manages may adopt effective approaches to promote their WR rankings according to the hints given by WRES.