Evaluating strategies for similarity search on the web
- 7 May 2002
- proceedings article
- Published by Association for Computing Machinery (ACM)
- p. 432-442
- https://doi.org/10.1145/511446.511502
Abstract
Finding pages on the Web that are similar to a query page (Related Pages) is an important component of modern search engines. A variety of strategies have been proposed for answering Related Pages queries, but comparative evaluation by user studies is expensive, especially when large strategy spaces must be searched (e.g., when tuning parameters). We present a technique for automatically evaluating strategies using Web hierarchies, such as Open Directory, in place of user feedback. We apply this evaluation methodology to a mix of document representation strategies, including the use of text, anchor-text, and links. We discuss the relative advantages and disadvantages of the various approaches examined. Finally, we describe how to efficiently construct a similarity index out of our chosen strategies, and provide sample results from our index.Keywords
This publication has 7 references indexed in Scilit:
- Topical locality in the WebPublished by Association for Computing Machinery (ACM) ,2000
- Data clusteringACM Computing Surveys, 1999
- Finding related pages in the World Wide WebComputer Networks, 1999
- Measures of distributional similarityPublished by Association for Computational Linguistics (ACL) ,1999
- Enhanced hypertext categorization using hyperlinksPublished by Association for Computing Machinery (ACM) ,1998
- Min-wise independent permutations (extended abstract)Published by Association for Computing Machinery (ACM) ,1998
- An algorithm for suffix strippingProgram: electronic library and information systems, 1980