WWW2007: Program
Top of Menu Home CFP Program Committees Key Dates Location Hotel Registration Students Sponsors Media Submission Tutorials Workshops Travel Info Proceedings

Poster Papers

Track: Search

Paper Title:
Classifying Web Sites

Authors:

  • Christoph Lindemann (University of Leipzig)
  • Lars Littig (University of Leipzig)

Abstract:
In this paper, we present a novel method for the classification of Web sites. This method exploits both structure and content of Web sites in order to discern their functionality. It allows for distinguishing between eight of the most relevant functional classes of Web sites. We show that a pre-classification of Web sites utilizing structural properties considerably improves a subsequent textual classification with standard techniques. We evaluate this approach on a dataset comprising more than 16,000 Web sites with about 20 million crawled and 100 million known Web pages. Our approach achieves an accuracy of 92% for the coarse-grained classification of these Web sites.

PDF version

























sponsors