Terms, Topics & Tasks: Enhanced User Modelling for Better Personalization

Given the distinct preferences of different users while using search engines, search personalization has become an important problem in information retrieval. Most approaches to search personalization are based on identifying topics a user may be interested in and personalizing search results based on this information. While topical interests information of users can be highly valuable in personalizing search results and improving user experience, it ignores the fact that two different users that have similar topical interests may still be interested in achieving very different tasks with respect to this topic (e.g. the type of tasks a broker is likely to perform related to finance is likely to be very different than that of a regular investor). Hence, considering user's topical interests jointly with the type of tasks they are likely to be interested in could result in better personalised We present an approach that uses search task information embedded in search logs to represent users by their actions over a task-space as well as over their topical-interest space. In particular, we describe a tensor based approach that represents each user in terms of (i) user's topical interests and (ii) user's search task behaviours in a coupled fashion and use these representations for personalization. Additionally, we also integrate user's historic search behavior in a coupled matrix-tensor factorization framework to learn user representations. Through extensive evaluation via query recommendations and user cohort analysis, we demonstrate the value of considering topic specific task information while developing user models.

[1]  Yang Song,et al.  A task level metric for measuring web search satisfaction and its application on improving relevance estimation , 2011, CIKM '11.

[2]  Scott Sanner,et al.  Learning Community-Based Preferences via Dirichlet Process Mixtures of Gaussian Processes , 2013, IJCAI.

[3]  ChengXiang Zhai,et al.  User modeling in search logs via a nonparametric bayesian approach , 2014, WSDM.

[4]  Ji-Rong Wen,et al.  WWW 2007 / Track: Search Session: Personalization A Largescale Evaluation and Analysis of Personalized Search Strategies ABSTRACT , 2022 .

[5]  Rosie Jones,et al.  Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs , 2008, CIKM '08.

[6]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[7]  Hui Xiong,et al.  Understanding of Internal Clustering Validation Measures , 2010, 2010 IEEE International Conference on Data Mining.

[8]  Daniel M. Dunlavy,et al.  A scalable optimization approach for fitting canonical tensor decompositions , 2011 .

[9]  Fabio Crestani,et al.  Building user profiles from topic models for personalised search , 2013, CIKM.

[10]  Susan Gauch,et al.  Personalizing Search Based on User Search Histories , 2004 .

[11]  Michael A. Shepherd,et al.  A Field Study Characterizing Web-based Information Seeking Tasks , 2022 .

[12]  Emine Yilmaz,et al.  Towards Hierarchies of Search Tasks & Subtasks , 2015, WWW.

[13]  Åke Björck,et al.  Least Squares Problems , 2009, Encyclopedia of Optimization.

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

[15]  Wei Chu,et al.  Enhancing personalized search by mining and modeling task behavior , 2013, WWW.

[16]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[17]  Wei Chu,et al.  Learning to extract cross-session search tasks , 2013, WWW.

[18]  Hongbo Deng,et al.  Identifying and labeling search tasks via query-based hawkes processes , 2014, KDD.

[19]  Yang Song,et al.  Evaluating the effectiveness of search task trails , 2012, WWW.

[20]  Tamara G. Kolda,et al.  All-at-once Optimization for Coupled Matrix and Tensor Factorizations , 2011, ArXiv.

[21]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[22]  Bonnie MacKay,et al.  Exploring multi-session web tasks , 2008, CHI.

[23]  Emine Yilmaz,et al.  Task-Based User Modelling for Personalization via Probabilistic Matrix Factorization , 2014, RecSys Posters.

[24]  Filip Radlinski,et al.  Personalizing web search using long term browsing history , 2011, WSDM '11.

[25]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[26]  G. Meurant.  Least Squares Problems , 2018, Explorations in Numerical Analysis.

[27]  Susan T. Dumais,et al.  Personalizing Search via Automated Analysis of Interests and Activities , 2005, SIGIR.

[28]  ChengXiang Zhai,et al.  A session-based search engine , 2004, SIGIR '04.

[29]  Fabrizio Silvestri,et al.  Identifying task-based sessions in search engine query logs , 2011, WSDM '11.

[30]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Andrew Postlewaite,et al.  Social Norms and Social Assets , 2011 .

[32]  Ryen W. White,et al.  Modeling and analysis of cross-session search tasks , 2011, SIGIR.

[33]  A. Stegeman,et al.  On Kruskal's uniqueness condition for the Candecomp/Parafac decomposition , 2007 .

[34]  Ryen W. White,et al.  Supporting Complex Search Tasks , 2014, CIKM.

[35]  Feng Qiu,et al.  Automatic identification of user interest for personalized search , 2006, WWW '06.