%0 Conference Paper %1 Taksa2007 %A Taksa, Isak %A Zelikovitz, Sarah %A Spink, Amanda %B ITNG '07: Proceedings of the International Conference on Information Technology %C Washington, DC, USA %D 2007 %I IEEE Computer Society %K IUI09 query_log_analysis %P 469--474 %R http://dx.doi.org/10.1109/ITNG.2007.202 %T Using Web Search Logs to Identify Query Classification Terms %U http://portal.acm.org/citation.cfm?id=1262257.1262320&coll=Portal&dl=GUIDE&CFID=2150660&CFTOKEN=37817046 %X Classification of search queries is a complex and computationally challenging task. Typically, search queries are short, reveal very few features per single query and are therefore a weak source for traditional machine learning. In this paper, we present a method that combines limited manual labeling, computational linguistics and information retrieval to classify a large collection of web search queries. A short set of manually chosen terms that are known a priori to be of interest to a particular class is used to cull a small number of actual queries from a commercial search engine log. These queries are then submitted to a commercial search engine and the returned search results are used to find more class related terms. We examine classification proficiency of the proposed method on a large web search engine query log and show that up to 48% of the unlabeled set could be classified using this method. We discuss results of this research and its implications on the advancement of short text classification. %@ 0-7695-2776-0

@inproceedings{Taksa2007, abstract = {Classification of search queries is a complex and computationally challenging task. Typically, search queries are short, reveal very few features per single query and are therefore a weak source for traditional machine learning. In this paper, we present a method that combines limited manual labeling, computational linguistics and information retrieval to classify a large collection of web search queries. A short set of manually chosen terms that are known a priori to be of interest to a particular class is used to cull a small number of actual queries from a commercial search engine log. These queries are then submitted to a commercial search engine and the returned search results are used to find more class related terms. We examine classification proficiency of the proposed method on a large web search engine query log and show that up to 48% of the unlabeled set could be classified using this method. We discuss results of this research and its implications on the advancement of short text classification.}, added-at = {2008-09-09T13:01:06.000+0200}, address = {Washington, DC, USA}, author = {Taksa, Isak and Zelikovitz, Sarah and Spink, Amanda}, biburl = {https://www.bibsonomy.org/bibtex/2a3789a42fefa2b2439ead6bcba744ff4/chriskoerner}, booktitle = {ITNG '07: Proceedings of the International Conference on Information Technology}, description = {Using Web Search Logs to Identify Query Classification Terms}, doi = {http://dx.doi.org/10.1109/ITNG.2007.202}, interhash = {d0d661dffb0e6f5d9f298f9203129e19}, intrahash = {a3789a42fefa2b2439ead6bcba744ff4}, isbn = {0-7695-2776-0}, keywords = {IUI09 query_log_analysis}, pages = {469--474}, publisher = {IEEE Computer Society}, timestamp = {2008-09-09T13:01:06.000+0200}, title = {Using Web Search Logs to Identify Query Classification Terms}, url = {http://portal.acm.org/citation.cfm?id=1262257.1262320&coll=Portal&dl=GUIDE&CFID=2150660&CFTOKEN=37817046}, year = 2007 }