Mining user web search activity with layered bayesian networks or how to capture a click in its context Export

@inproceedings{citeulike:5839789, abstract = {Mining user web search activity potentially has a broad range of applications including web result pre-fetching, automatic search query reformulation, click spam detection, estimation of document relevance and prediction of user satisfaction. This analysis is difficult because the data recorded by search engines while users interact with them, although abundant, is very noisy. In this work, we explore the utility of mining search behavior of users, represented by observed variables including the time the user spends on the page, and whether the user reformulated his or her query. As a case study, we examine the contribution this data makes to predicting the relevance of a document in the absence of document content models. To this end, we first propose a method for grouping the interactions of a particular user according to the different tasks he or she undertakes. With each task corresponding to a distinct information need, we then propose a Bayesian Network to holistically model these interactions. The aim is to identify distinct patterns of search behaviors. Finally, we join these patterns to a list of custom features and we use gradient boosted decision trees to predict the relevance of a set of query document pairs for which we have relevance assessments. The experimental results confirm the potential of our model, with significant improvements in precision for predicting the relevance of documents based on a model of the user's search and click behavior, over a baseline model using only click and query features, with no Bayesian Network input.}, address = {New York, NY, USA}, author = {Piwowarski, Benjamin and Dupret, Georges and Jones, Rosie}, booktitle = {WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining}, citeulike-article-id = {5839789}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1498759.1498823}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1498759.1498823}, doi = {10.1145/1498759.1498823}, isbn = {978-1-60558-390-7}, keywords = {analysis, behavior, engine, information, log, query, retrieval, search, user}, location = {Barcelona, Spain}, pages = {162--171}, posted-at = {2009-09-25 11:02:03}, priority = {2}, publisher = {ACM}, title = {Mining user web search activity with layered bayesian networks or how to capture a click in its context}, url = {http://dx.doi.org/10.1145/1498759.1498823}, year = {2009} }

TY - CONF ID - citeulike:5839789 L3 - citeulike-article-id:5839789 N2 - Mining user web search activity potentially has a broad range of applications including web result pre-fetching, automatic search query reformulation, click spam detection, estimation of document relevance and prediction of user satisfaction. This analysis is difficult because the data recorded by search engines while users interact with them, although abundant, is very noisy. In this work, we explore the utility of mining search behavior of users, represented by observed variables including the time the user spends on the page, and whether the user reformulated his or her query. As a case study, we examine the contribution this data makes to predicting the relevance of a document in the absence of document content models. To this end, we first propose a method for grouping the interactions of a particular user according to the different tasks he or she undertakes. With each task corresponding to a distinct information need, we then propose a Bayesian Network to holistically model these interactions. The aim is to identify distinct patterns of search behaviors. Finally, we join these patterns to a list of custom features and we use gradient boosted decision trees to predict the relevance of a set of query document pairs for which we have relevance assessments. The experimental results confirm the potential of our model, with significant improvements in precision for predicting the relevance of documents based on a model of the user's search and click behavior, over a baseline model using only click and query features, with no Bayesian Network input. CY - Barcelona, Spain SN - 978-1-60558-390-7 AD - New York, NY, USA EP - 171 TI - Mining user web search activity with layered bayesian networks or how to capture a click in its context PB - ACM T2 - WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining SP - 162 KW - analysis KW - behavior KW - engine KW - information KW - log KW - query KW - retrieval KW - search KW - user AU - Piwowarski, Benjamin AU - Dupret, Georges AU - Jones, Rosie PY - 2009/// UR - http://dx.doi.org/10.1145/1498759.1498823 ER -