N. Craswell, and M. Szummer. SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, page 239--246. New York, NY, USA, ACM, (2007)
DOI: 10.1145/1277741.1277784
Abstract
Search engines can record which documents were clicked for which query, and use these query-document pairs as "soft" relevance judgments. However, compared to the true judgments, click logs give noisy and sparse relevance information. We apply a Markov random walk model to a large click log, producing a probabilistic ranking of documents for a given query. A key advantage of the model is its ability to retrieve relevant documents that have not yet been clicked for that query and rank those effectively. We conduct experiments on click logs from image search, comparing our ("backward") random walk model to a different ("forward") random walk, varying parameters such as walk length and self-transition probability. The most effective combination is a long backward walk with high self-transition probability.
%0 Conference Paper
%1 craswell2007click
%A Craswell, Nick
%A Szummer, Martin
%B SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 2007
%I ACM
%K clicks, clustering, queries, web-graph
%P 239--246
%R 10.1145/1277741.1277784
%T Random walks on the click graph
%U http://dx.doi.org/10.1145/1277741.1277784
%X Search engines can record which documents were clicked for which query, and use these query-document pairs as "soft" relevance judgments. However, compared to the true judgments, click logs give noisy and sparse relevance information. We apply a Markov random walk model to a large click log, producing a probabilistic ranking of documents for a given query. A key advantage of the model is its ability to retrieve relevant documents that have not yet been clicked for that query and rank those effectively. We conduct experiments on click logs from image search, comparing our ("backward") random walk model to a different ("forward") random walk, varying parameters such as walk length and self-transition probability. The most effective combination is a long backward walk with high self-transition probability.
%@ 978-1-59593-597-7
@inproceedings{craswell2007click,
abstract = {Search engines can record which documents were clicked for which query, and use these query-document pairs as "soft" relevance judgments. However, compared to the true judgments, click logs give noisy and sparse relevance information. We apply a Markov random walk model to a large click log, producing a probabilistic ranking of documents for a given query. A key advantage of the model is its ability to retrieve relevant documents that have not yet been clicked for that query and rank those effectively. We conduct experiments on click logs from image search, comparing our ("backward") random walk model to a different ("forward") random walk, varying parameters such as walk length and self-transition probability. The most effective combination is a long backward walk with high self-transition probability.},
added-at = {2009-08-06T15:16:38.000+0200},
address = {New York, NY, USA},
author = {Craswell, Nick and Szummer, Martin},
biburl = {https://www.bibsonomy.org/bibtex/2023cd287dfe5bc88d8eb05c5d9e767c0/chato},
booktitle = {SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval},
citeulike-article-id = {1542207},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1277741.1277784},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1277741.1277784},
citeulike-linkout-2 = {http://research.microsoft.com/users/Cambridge/szummer/papers/CraswellSzummer-random-walks-sigir07.pdf},
doi = {10.1145/1277741.1277784},
interhash = {d816d03b4dacceb8869596ade1d86465},
intrahash = {023cd287dfe5bc88d8eb05c5d9e767c0},
isbn = {978-1-59593-597-7},
keywords = {clicks, clustering, queries, web-graph},
location = {Amsterdam, The Netherlands},
pages = {239--246},
posted-at = {2007-09-28 10:28:03},
priority = {0},
publisher = {ACM},
timestamp = {2009-08-06T15:16:47.000+0200},
title = {Random walks on the click graph},
url = {http://dx.doi.org/10.1145/1277741.1277784},
year = 2007
}