Recognizing Nepotistic Links on the Web

The use of link analysis and page popularity in search engines has grown recently to improve query result rankings. Since the number of such links contributes to the value of the document in such calculations, we wish to recognize and eliminate nepotistic links --- links between pages that are present for reasons other than merit. This paper explores some of the issues surrounding the question of what links to keep, and we report high accuracy in initial experiments to show the potential for using a machine learning tool to automatically recognize such links.

Presented at the AAAI-2000 Workshop on Artificial Intelligence for Web Search, Austin, TX, July 30, and published in Artificial Intelligence for Web Search, Technical Report WS-00-01, pp. 23-28, AAAI Press.

Back to Brian Davison's publications