Baeza-Yates, R. & Tiberi, A.: Extracting semantic relations from query logs. KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NY, USA: ACM, 2007, S. 76-85
[Volltext]
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 first 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{baezayates2007extracting,
author = {Baeza-Yates, Ricardo and Tiberi, Alessandro},
title = {Extracting semantic relations from query logs},
booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining},
publisher = {ACM},
address = {New York, NY, USA},
year = {2007},
pages = {76--85},
url = {http://portal.acm.org/citation.cfm?id=1281192.1281204},
doi = {http://doi.acm.org/10.1145/1281192.1281204},
isbn = {978-1-59593-609-7},
keywords = {analysis, iin2009, kdd2007, ol_web2.0, ontology_learning, query_log, toread, toread_dbe, widely_related},
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 first 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.}
}