Query logs provide a valuable resource for preference information in search. A user clicking on a specific resource after submitting a query indicates that the resource has some relevance with respect to the query. To leverage the information ofquery logs, one can relate submitted queries from specific users to their clicked resources and build a tripartite graph ofusers, resources and queries. This graph resembles the folksonomy structure of social bookmarking systems, where users addtags to resources. In this article, we summarize our work on building folksonomies from query log files. The focus is on threecomparative studies of the system’s content, structure and semantics. Our results show that query logs incorporate typicalfolksonomy properties and that approaches to leverage the inherent semantics of folksonomies can be applied to query logsas well.

@article{benz2010query, author = {Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Stumme, Gerd}, title = {Query Logs as Folksonomies}, journal = {Datenbank-Spektrum}, year = {2010}, volume = {10}, number = {1}, pages = {15--24}, url = {http://dx.doi.org/10.1007/s13222-010-0004-8}, keywords = {2010, folksonomy, itegpub, logsonomy, myown}, abstract = {Query logs provide a valuable resource for preference information in search. A user clicking on a specific resource after submitting a query indicates that the resource has some relevance with respect to the query. To leverage the information ofquery logs, one can relate submitted queries from specific users to their clicked resources and build a tripartite graph ofusers, resources and queries. This graph resembles the folksonomy structure of social bookmarking systems, where users addtags to resources. In this article, we summarize our work on building folksonomies from query log files. The focus is on threecomparative studies of the system’s content, structure and semantics. Our results show that query logs incorporate typicalfolksonomy properties and that approaches to leverage the inherent semantics of folksonomies can be applied to query logsas well. } }

%0 = article %A = Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Stumme, Gerd %D = 2010 %T = Query Logs as Folksonomies %U = http://dx.doi.org/10.1007/s13222-010-0004-8

Web search queries capture the information need of search engine users. Search engines store these queries in their logs and analyze them to guide their search results.In this work, we argue that not only a search engine can benefit from data stored in these logs, but also the web users. We first show how clickthrough logs can be collected in a distributed fashion using the http referer field in web server access logs. We then perform a set of experiments to study the information value of search engine queries when treated as "tags" or "labels" for the web pages that both appear as a result and the user actually clicks on. We ask how much extra information these query tags provide for web pagesby comparing them to tags from the del.icio.us bookmarking site and to the pagetext. We find that query tags can provide substantially many (on average 250 tags per URL), new tags (on average 125 tags per URL are not present in the pagetext) for a large fraction of the Web.

@inproceedings{antonellis2009tagging, author = {Antonellis, Ioannis and Garcia-Molina, Hector and Karim, Jawed}, title = {Tagging with Queries: How and Why?}, editor = {Baeza-Yates, Ricardo A. and Boldi, Paolo and Ribeiro-Neto, Berthier A. and Cambazoglu, Berkant Barla}, booktitle = {WSDM (Late Breaking-Results)}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, url = {http://www.wsdm2009.org/wsdm2009_antonellis.pdf}, isbn = {978-1-60558-390-7}, keywords = {tagging, logsonomy, search_engine}, abstract = {Web search queries capture the information need of search engine users. Search engines store these queries in their logs and analyze them to guide their search results.In this work, we argue that not only a search engine can benefit from data stored in these logs, but also the web users. We first show how clickthrough logs can be collected in a distributed fashion using the http referer field in web server access logs. We then perform a set of experiments to study the information value of search engine queries when treated as "tags" or "labels" for the web pages that both appear as a result and the user actually clicks on. We ask how much extra information these query tags provide for web pagesby comparing them to tags from the del.icio.us bookmarking site and to the pagetext. We find that query tags can provide substantially many (on average 250 tags per URL), new tags (on average 125 tags per URL are not present in the pagetext) for a large fraction of the Web.} }

%0 = inproceedings %A = Antonellis, Ioannis and Garcia-Molina, Hector and Karim, Jawed %B = WSDM (Late Breaking-Results) %C = New York, NY, USA %D = 2009 %I = ACM %T = Tagging with Queries: How and Why? %U = http://www.wsdm2009.org/wsdm2009_antonellis.pdf

In social bookmarking systems users describe bookmarksby keywords called tags. The structure behindthese social systems, called folksonomies, can beviewed as a tripartite hypergraph of user, tag and resourcenodes. This underlying network shows specificstructural properties that explain its growth and the possibilityof serendipitous exploration.Search engines filter the vast information of the web.Queries describe a user’s information need. In responseto the displayed results of the search engine, users clickon the links of the result page as they expect the answerto be of relevance. The clickdata can be represented as afolksonomy in which queries are descriptions of clickedURLs. This poster analyzes the topological characteristicsof the resulting tripartite hypergraph of queries,users and bookmarks of two query logs and compares ittwo a snapshot of the folksonomy del.icio.us.

@inproceedings{jaeschke2008logsonomy, author = {Jäschke, Robert and Krause, Beate and Hotho, Andreas and Stumme, Gerd}, title = {Logsonomy -- A Search Engine Folksonomy}, booktitle = {Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008)}, publisher = {AAAI Press}, year = {2008}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2008/Krause2008logsonomy_short.pdf}, keywords = {2008, search, engine, logsonomy, logsonomies, folksonomy, tagorapub, folksonomies, itegpub}, abstract = {In social bookmarking systems users describe bookmarksby keywords called tags. The structure behindthese social systems, called folksonomies, can beviewed as a tripartite hypergraph of user, tag and resourcenodes. This underlying network shows specificstructural properties that explain its growth and the possibilityof serendipitous exploration.Search engines filter the vast information of the web.Queries describe a user’s information need. In responseto the displayed results of the search engine, users clickon the links of the result page as they expect the answerto be of relevance. The clickdata can be represented as afolksonomy in which queries are descriptions of clickedURLs. This poster analyzes the topological characteristicsof the resulting tripartite hypergraph of queries,users and bookmarks of two query logs and compares ittwo a snapshot of the folksonomy del.icio.us.} }

%0 = inproceedings %A = Jäschke, Robert and Krause, Beate and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the Second International Conference on Weblogs and Social Media(ICWSM 2008) %D = 2008 %I = AAAI Press %T = Logsonomy -- A Search Engine Folksonomy %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2008/Krause2008logsonomy_short.pdf

@inproceedings{gwizdka2007finding, author = {Gwizdka, Jacek and Cole, Michael}, title = {Finding It on Google, Finding It on del.icio.us.}, editor = {Kovács, László and Fuhr, Norbert and Meghini, Carlo}, booktitle = {ECDL}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2007}, volume = {4675}, pages = {559-562}, url = {http://dblp.uni-trier.de/db/conf/ercimdl/ecdl2007.html#GwizdkaC07}, isbn = {978-3-540-74850-2}, keywords = {search, logsonomy, levsem09, folksonomy} }

%0 = inproceedings %A = Gwizdka, Jacek and Cole, Michael %B = ECDL %D = 2007 %I = Springer %T = Finding It on Google, Finding It on del.icio.us. %U = http://dblp.uni-trier.de/db/conf/ercimdl/ecdl2007.html#GwizdkaC07

@inproceedings{yanbe2007can, author = {Yanbe, Yusuke and Jatowt, Adam and Nakamura, Satoshi and Tanaka, Katsumi}, title = {Can social bookmarking enhance search in the web?}, booktitle = {JCDL '07: Proceedings of the 2007 conference on Digital libraries}, publisher = {ACM Press}, address = {New York, NY, USA}, year = {2007}, pages = {107--116}, url = {http://portal.acm.org/citation.cfm?id=1255175.1255198}, doi = {http://doi.acm.org/10.1145/1255175.1255198}, isbn = {978-1-59593-644-8}, keywords = {search, logsonomy, social_bookmarking, folksonomy} }

%0 = inproceedings %A = Yanbe, Yusuke and Jatowt, Adam and Nakamura, Satoshi and Tanaka, Katsumi %B = JCDL '07: Proceedings of the 2007 conference on Digital libraries %C = New York, NY, USA %D = 2007 %I = ACM Press %T = Can social bookmarking enhance search in the web? %U = http://portal.acm.org/citation.cfm?id=1255175.1255198