Learning to Personalize for Web Search Sessions

The task of session search focuses on using interaction data to improve relevance for the user's next query at the session level. In this paper, we formulate session search as a personalization task under the framework of learning to rank. Personalization approaches re-rank results to match a user model. Such user models are usually accumulated over time based on the user's browsing behaviour. We use a pre-computed and transparent set of user models based on concepts from the social science literature. Interaction data are used to map each session to these user models. Novel features are then estimated based on such models as well as sessions' interaction data. Extensive experiments on test collections from the TREC session track show statistically significant improvements over current session search algorithms.

[1]  Wei Chu,et al.  Modeling the impact of short- and long-term behavior on search personalization , 2012, SIGIR '12.

[2]  Robert Krovetz,et al.  Viewing morphology as an inference process , 1993, Artif. Intell..

[3]  Susan T. Dumais,et al.  Improving Web Search Ranking by Incorporating User Behavior Information , 2019, SIGIR Forum.

[4]  Nicholas J. Belkin,et al.  A faceted approach to conceptualizing tasks in information seeking , 2008, Inf. Process. Manag..

[5]  Filip Radlinski,et al.  Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search , 2007, TOIS.

[6]  Grace Hui Yang,et al.  Utilizing query change for session search , 2013, SIGIR.

[7]  Ramesh Nallapati,et al.  Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora , 2009, EMNLP.

[8]  Koby Crammer,et al.  Adaptive regularization of weight vectors , 2009, Machine Learning.

[9]  Grace Hui Yang,et al.  Is the First Query the Most Important: An Evaluation of Query Aggregation Schemes in Session Search , 2014, AIRS.

[10]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[11]  Grace Hui Yang,et al.  Modeling Rich Interactions in Session Search - Georgetown University at TREC 2014 Session Track , 2014, TREC.

[12]  Ben Carterette,et al.  Overview of the TREC 2011 Session Track , 2011, TREC.

[13]  W. Bruce Croft,et al.  Relevance-Based Language Models , 2001, SIGIR '01.

[14]  Charles L. A. Clarke,et al.  Efficient and effective spam filtering and re-ranking for large web datasets , 2010, Information Retrieval.

[15]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[16]  Y.-S. Shih,et al.  Families of splitting criteria for classification trees , 1999, Stat. Comput..

[17]  Jong-Hak Lee,et al.  Analyses of multiple evidence combination , 1997, SIGIR '97.

[18]  Xuehua Shen,et al.  Context-sensitive information retrieval using implicit feedback , 2005, SIGIR '05.

[19]  Luo Si,et al.  Supervised Local Contexts Aggregation for Effective Session Search , 2016, ECIR.

[20]  Pavel Serdyukov,et al.  Personalization of web-search using short-term browsing context , 2013, CIKM.

[21]  Nicholas J. Belkin,et al.  Personalization of search results using interaction behaviors in search sessions , 2012, SIGIR '12.

[22]  ZaragozaHugo,et al.  The Probabilistic Relevance Framework , 2009 .

[23]  W. Bruce Croft,et al.  A Language Modeling Approach to Information Retrieval , 1998, SIGIR Forum.

[24]  Ben Carterette,et al.  Evaluating Retrieval over Sessions: The TREC Session Track 2011-2014 , 2016, SIGIR.

[25]  Djoerd Hiemstra,et al.  A Linguistically Motivated Probabilistic Model of Information Retrieval , 1998, ECDL.

[26]  Dawei Song,et al.  How Different Features Contribute to the Session Search? , 2015, NLPCC.

[27]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Shuguang Han,et al.  On Duplicate Results in a Search Session , 2012, TREC.

[29]  Steve Fox,et al.  Evaluating implicit measures to improve web search , 2005, TOIS.

[30]  Stanley Wasserman,et al.  Social Network Analysis: Methods and Applications , 1994, Structural analysis in the social sciences.

[31]  Jianfeng Gao,et al.  Ranking, Boosting, and Model Adaptation , 2008 .

[32]  Yiqun Liu,et al.  Improving Session Search Performance with a Multi-MDP Model , 2018, AIRS.

[33]  Daqing He,et al.  Pitt at TREC 2013: Different Effects of Click-through and Past Queries on Whole-session Search Performance , 2013, TREC.

[34]  Abdur Chowdhury,et al.  A picture of search , 2006, InfoScale '06.

[35]  Grace Hui Yang,et al.  Session search modeling by partially observable Markov decision process , 2018, Information Retrieval Journal.

[36]  Milad Shokouhi,et al.  Fighting search engine amnesia: reranking repeated results , 2013, SIGIR.

[37]  Nir Levine,et al.  An Extended Relevance Model for Session Search , 2017, SIGIR.

[38]  Maarten de Rijke,et al.  Lexical Query Modeling in Session Search , 2016, ICTIR.

[39]  Grace Hui Yang,et al.  Session Search by Direct Policy Learning , 2015, ICTIR.

[40]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[41]  Grace Hui Yang,et al.  Win-win search: dual-agent stochastic game in session search , 2014, SIGIR.

[42]  Hugo Zaragoza,et al.  The Probabilistic Relevance Framework: BM25 and Beyond , 2009, Found. Trends Inf. Retr..