| Category | Value | ||
| Available via | http://dbpubs.stanford.edu/pub/2002-7 | ||
| Previous version | 2001-8 | ||
| Submitted on | 14th of February 2002 | ||
| Author | Haveliwala, Taher H.; Gionis, Aristides; Klein, Dan; Indyk, Piotr | ||
| Title | Evaluating Strategies for Similarity Search on the Web | ||
| Date of publication | 2002 | ||
| Published in | WWW-2002 | ||
| Citation | Taher H. Haveliwala, Aristides Gionis, Dan Klein, and Piotr Indyk. Evaluating Strategies for Similarity Search on the Web. To appear in Proceedings of the Eleventh International World Wide Web Conference, 2002. | ||
| Number of pages | 10 | ||
| Language | English | ||
| Project | Stanford InfoLab; Database Group; Natural Language Processing Group | ||
| Type | Conference or Journal Paper | ||
| Subject group | Data Mining; Databases and the Web | ||
| 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 | related pages, similarity search, search, evaluation, Open Directory Project | ||
| Sponsored by |
NSF Grant IIS-0085896 NSF Grant IIS-0118173 NSF Graduate Research Fellowship Microsoft Research Graduate Fellowship | ||
| Fulltext source |
| Management of the document by | siroker@db.stanford.edu
| |