Improving web search ranking by incorporating user behavior information
作者： Eugene Agichtein , Eric Brill , Susan Dumais
关键词:
摘要: We show that incorporating user behavior data can significantly improve ordering of top results in real web search setting. examine alternatives for feedback into the ranking process and explore contributions compared to other common features. report a large scale evaluation over 3,000 queries 12 million interactions with popular engine. implicit augment features, improving accuracy competitive algorithms by as much 31% relative original performance.
acm.org
fit.edu
dal.ca 参考文章(28)
Suchi Saria, Nick Craswell, Hugo Zaragoza, Stephen E. Robertson, Michael J. Taylor, Microsoft Cambridge at TREC 13: Web and Hard Tracks. text retrieval conference. ,(2004)
Max Chickering, The WinMine Toolkit ,(2017)
Kuldeep Karnawat, Susan T. Dumais, Mark Mydland, Thomas White, Sean Fox, Evaluating implicit measures to improve the search experiences ACM Transactions on Information Systems. ,(2003)
Douglas W Oard, Jinmook Kim, Modeling Information Content Using Observable Behavior Proceedings of the ASIST Annual Meeting. ,vol. 38, pp. 481- ,(2001)
Thorsten Joachims, Making large scale SVM learning practical Technical reports. ,(1999) , 10.17877/DE290R-14262
Peter Pirolli, The Use of Proximal Information Scent to Forage for Distal Content on the World Wide Web ,(2004)
Douglas W Oard, Jinmook Kim, Implicit Feedback for Recommender Systems pp. 81- ,(1998)
r;ribeiro-neto bueza-yates (b), Modern Information Retrieval ,(1999)
Thorsten Joachims, Filip Radlinski, Evaluating the Robustness of Learning from Implicit Feedback arXiv: Learning. ,(2006)
Gerard Salton, Michael J. McGill, Introduction to Modern Information Retrieval ,(1983)