Given a terabyte click log, can we build an efficient and effective click model? It is commonly believed that web search click logs are a gold mine for search business, because they reflect users' preference over web documents presented by the search engine. Click models provide a principled approach to inferring user-perceived relevance of web documents, which can be leveraged in numerous applications in search businesses. Due to the huge volume of click data, scalability is a must. We present the click chain model (CCM), which is based on a solid, Bayesian framework. It is both scalable and incremental, perfectly meeting the computational challenges imposed by the voluminous click logs that constantly grow. We conduct an extensive experimental study on a data set containing 8.8 million query sessions obtained in July 2008 from a commercial search engine. CCM consistently outperforms two state-of-the-art competitors in a number of metrics, with over 9.7\% better log-likelihood, over 6.2\% better click perplexity and much more robust (up to 30\%) prediction of the first and the last clicked position.
%0 Conference Paper
%1 citeulike:4374905
%A Guo, Fan
%A Liu, Chao
%A Kannan, Anitha
%A Minka, Tom
%A Taylor, Michael
%A Wang, Yi M.
%A Faloutsos, Christos
%B Proceedings of the 18th International Conference on World Wide Web
%C New York, NY, USA
%D 2009
%I ACM
%K adaptive-web-search personalized-search social-search
%P 11--20
%R 10.1145/1526709.1526712
%T Click Chain Model in Web Search
%U http://dx.doi.org/10.1145/1526709.1526712
%X Given a terabyte click log, can we build an efficient and effective click model? It is commonly believed that web search click logs are a gold mine for search business, because they reflect users' preference over web documents presented by the search engine. Click models provide a principled approach to inferring user-perceived relevance of web documents, which can be leveraged in numerous applications in search businesses. Due to the huge volume of click data, scalability is a must. We present the click chain model (CCM), which is based on a solid, Bayesian framework. It is both scalable and incremental, perfectly meeting the computational challenges imposed by the voluminous click logs that constantly grow. We conduct an extensive experimental study on a data set containing 8.8 million query sessions obtained in July 2008 from a commercial search engine. CCM consistently outperforms two state-of-the-art competitors in a number of metrics, with over 9.7\% better log-likelihood, over 6.2\% better click perplexity and much more robust (up to 30\%) prediction of the first and the last clicked position.
%@ 978-1-60558-487-4
@inproceedings{citeulike:4374905,
abstract = {{Given a terabyte click log, can we build an efficient and effective click model? It is commonly believed that web search click logs are a gold mine for search business, because they reflect users' preference over web documents presented by the search engine. Click models provide a principled approach to inferring user-perceived relevance of web documents, which can be leveraged in numerous applications in search businesses. Due to the huge volume of click data, scalability is a must. We present the click chain model (CCM), which is based on a solid, Bayesian framework. It is both scalable and incremental, perfectly meeting the computational challenges imposed by the voluminous click logs that constantly grow. We conduct an extensive experimental study on a data set containing 8.8 million query sessions obtained in July 2008 from a commercial search engine. CCM consistently outperforms two state-of-the-art competitors in a number of metrics, with over 9.7\% better log-likelihood, over 6.2\% better click perplexity and much more robust (up to 30\%) prediction of the first and the last clicked position.}},
added-at = {2017-11-15T17:02:25.000+0100},
address = {New York, NY, USA},
author = {Guo, Fan and Liu, Chao and Kannan, Anitha and Minka, Tom and Taylor, Michael and Wang, Yi M. and Faloutsos, Christos},
biburl = {https://www.bibsonomy.org/bibtex/2ce2ebc04c862b589a04a550635dafead/brusilovsky},
booktitle = {Proceedings of the 18th International Conference on World Wide Web},
citeulike-article-id = {4374905},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1526709.1526712},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1526709.1526712},
doi = {10.1145/1526709.1526712},
interhash = {1f2f8089643f2365cc5f3a6fe28021a7},
intrahash = {ce2ebc04c862b589a04a550635dafead},
isbn = {978-1-60558-487-4},
keywords = {adaptive-web-search personalized-search social-search},
location = {Madrid, Spain},
pages = {11--20},
posted-at = {2016-04-24 18:06:04},
priority = {2},
publisher = {ACM},
series = {WWW '09},
timestamp = {2020-07-15T02:34:26.000+0200},
title = {{Click Chain Model in Web Search}},
url = {http://dx.doi.org/10.1145/1526709.1526712},
year = 2009
}