R. Baeza-Yates, and A. Tiberi. KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, page 76--85. New York, NY, USA, ACM, (2007)description = Extracting semantic relations from query logs,
location = San Jose, California, USA,
isbn = 978-1-59593-609-7,
doi = http://doi.acm.org/10.1145/1281192.1281204.
Abstract
In this paper we study a large query log of more than twenty
million queries with the goal of extracting the semantic relations
that are implicitly captured in the actions of users
submitting queries and clicking answers. Previous query log
analyses were mostly done with just the queries and not the
actions that followed after them. We rst propose a novel
way to represent queries in a vector space based on a graph
derived from the query-click bipartite graph. We then analyze
the graph produced by our query log, showing that
it is less sparse than previous results suggested, and that
almost all the measures of these graphs follow power laws,
shedding some light on the searching user behavior as well
as on the distribution of topics that people want in the Web.
The representation we introduce allows to infer interesting
semantic relationships between queries. Second, we provide
an experimental analysis on the quality of these relations,
showing that most of them are relevant. Finally we sketch
an application that detects multitopical URLs.
description = Extracting semantic relations from query logs,
location = San Jose, California, USA,
isbn = 978-1-59593-609-7,
doi = http://doi.acm.org/10.1145/1281192.1281204
%0 Conference Paper
%1 paper:baeza-yattes:2007
%A Baeza-Yates, Ricardo
%A Tiberi, Alessandro
%B KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
%C New York, NY, USA
%D 2007
%I ACM
%K 2007 logd query relation search semantic
%P 76--85
%T Extracting semantic relations from query logs
%U http://portal.acm.org/citation.cfm?id=1281204
%X In this paper we study a large query log of more than twenty
million queries with the goal of extracting the semantic relations
that are implicitly captured in the actions of users
submitting queries and clicking answers. Previous query log
analyses were mostly done with just the queries and not the
actions that followed after them. We rst propose a novel
way to represent queries in a vector space based on a graph
derived from the query-click bipartite graph. We then analyze
the graph produced by our query log, showing that
it is less sparse than previous results suggested, and that
almost all the measures of these graphs follow power laws,
shedding some light on the searching user behavior as well
as on the distribution of topics that people want in the Web.
The representation we introduce allows to infer interesting
semantic relationships between queries. Second, we provide
an experimental analysis on the quality of these relations,
showing that most of them are relevant. Finally we sketch
an application that detects multitopical URLs.
@inproceedings{paper:baeza-yattes:2007,
abstract = {In this paper we study a large query log of more than twenty
million queries with the goal of extracting the semantic relations
that are implicitly captured in the actions of users
submitting queries and clicking answers. Previous query log
analyses were mostly done with just the queries and not the
actions that followed after them. We rst propose a novel
way to represent queries in a vector space based on a graph
derived from the query-click bipartite graph. We then analyze
the graph produced by our query log, showing that
it is less sparse than previous results suggested, and that
almost all the measures of these graphs follow power laws,
shedding some light on the searching user behavior as well
as on the distribution of topics that people want in the Web.
The representation we introduce allows to infer interesting
semantic relationships between queries. Second, we provide
an experimental analysis on the quality of these relations,
showing that most of them are relevant. Finally we sketch
an application that detects multitopical URLs.},
added-at = {2009-06-19T17:34:06.000+0200},
address = {New York, NY, USA},
author = {Baeza-Yates, Ricardo and Tiberi, Alessandro},
biburl = {https://www.bibsonomy.org/bibtex/26e45b65feffd1545c6dca62bf4b8f53d/praveen},
booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining},
interhash = {26ca034be705abaf072835784f53d877},
intrahash = {6e45b65feffd1545c6dca62bf4b8f53d},
keywords = {2007 logd query relation search semantic},
note = {description = {Extracting semantic relations from query logs},
location = {San Jose, California, USA},
isbn = {978-1-59593-609-7},
doi = {http://doi.acm.org/10.1145/1281192.1281204}},
pages = {76--85},
publisher = {ACM},
timestamp = {2009-06-19T17:34:06.000+0200},
title = {Extracting semantic relations from query logs},
url = {http://portal.acm.org/citation.cfm?id=1281204},
year = 2007
}