Additive Smoothing for Relevance-Based Language Modelling of Recommender Systems

The use of Relevance-Based Language Models for top-N recommendation has become a promising line of research. Previous works have used collection-based smoothing methods for this task. However, a recent analysis on RM1 (an estimation of Relevance-Based Language Models) in document retrieval showed that this type of smoothing methods demote the IDF effect in pseudo-relevance feedback. In this paper, we claim that the IDF effect from retrieval is closely related to the concept of novelty in recommendation. We perform an axiomatic analysis of the IDF effect on RM2 concluding that this kind of smoothing methods also demotes the IDF effect in recommendation. By axiomatic analysis, we find that a collection-agnostic method, Additive smoothing, does not demote this property. Our experiments confirm that this alternative improves the accuracy, novelty and diversity figures of the recommendations.

[1]  James Bennett,et al.  The Netflix Prize , 2007 .

[2]  Bracha Shapira,et al.  Recommender Systems Handbook , 2015, Springer US.

[3]  George Karypis,et al.  A Comprehensive Survey of Neighborhood-based Recommendation Methods , 2011, Recommender Systems Handbook.

[4]  Yuanzhi Li,et al.  A Theoretical Analysis of NDCG Ranking Measures , 2013 .

[5]  Liang He,et al.  Evaluating recommender systems , 2012, Seventh International Conference on Digital Information Management (ICDIM 2012).

[6]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[7]  Frederick Jelinek,et al.  Interpolated estimation of Markov source parameters from sparse data , 1980 .

[8]  Neil J. Hurley,et al.  Novelty and Diversity in Top-N Recommendation -- Analysis and Evaluation , 2011, TOIT.

[9]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[10]  Hermann Ney,et al.  On structuring probabilistic dependences in stochastic language modelling , 1994, Comput. Speech Lang..

[11]  Daniel Valcarce,et al.  Exploring Statistical Language Models for Recommender Systems , 2015, RecSys.

[12]  Yi-Cheng Zhang,et al.  Solving the apparent diversity-accuracy dilemma of recommender systems , 2008, Proceedings of the National Academy of Sciences.

[13]  Jun Wang,et al.  A User-Item Relevance Model for Log-Based Collaborative Filtering , 2006, ECIR.

[14]  David J. C. MacKay,et al.  A hierarchical Dirichlet language model , 1995, Natural Language Engineering.

[15]  Kartik Hosanagar,et al.  Blockbuster Culture's Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity , 2007, Manag. Sci..

[16]  Karen Sparck Jones.  A statistical interpretation of term specificity and its application in retrieval , 1972 .

[17]  Alvaro Barreiro,et al.  Language Models for Collaborative Filtering Neighbourhoods , 2016, ECIR.

[18]  Jun Wang,et al.  Noname manuscript No. (will be inserted by the editor) Bridging Memory-Based Collaborative Filtering and Text Retrieval , 2022 .

[19]  Alvaro Barreiro,et al.  Promoting Divergent Terms in the Estimation of Relevance Models , 2011, ICTIR.

[20]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[21]  Alejandro Bellogín,et al.  Relevance-based language modelling for recommender systems , 2013, Inf. Process. Manag..

[22]  George Karypis,et al.  A Comprehensive Survey of Neighborhood-based Recommendation Methods , 2011, Recommender Systems Handbook.

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

[24]  Alvaro Barreiro,et al.  A Study of Smoothing Methods for Relevance-Based Language Modelling of Recommender Systems , 2015, ECIR.

[25]  Alejandro Bellogín,et al.  Precision-oriented evaluation of recommender systems: an algorithmic comparison , 2011, RecSys '11.

[26]  Jonathan L. Herlocker,et al.  A collaborative filtering algorithm and evaluation metric that accurately model the user experience , 2004, SIGIR '04.

[27]  Peretz Shoval,et al.  Information Filtering: Overview of Issues, Research and Systems , 2001, User Modeling and User-Adapted Interaction.

[28]  Marti A. Hearst.  Chapter 2 of the second edition of Modern Information Retrieval Renamed Modern Information Retrieval : The Concepts and Technology behind Search , 2011 .

[29]  Nicholas J. Belkin,et al.  Information filtering and information retrieval: two sides of the same coin? , 1992, CACM.

[30]  Alvaro Barreiro,et al.  A Study of Priors for Relevance-Based Language Modelling of Recommender Systems , 2015, RecSys.

[31]  ChengXiang Zhai,et al.  Axiomatic Analysis of Smoothing Methods in Language Models for Pseudo-Relevance Feedback , 2015, ICTIR.

[32]  CHENGXIANG ZHAI,et al.  A study of smoothing methods for language models applied to information retrieval , 2004, TOIS.

[33]  Claudio Carpineto,et al.  An information-theoretic approach to automatic query expansion , 2001, TOIS.

[34]  Saul Vargas,et al.  Novelty and Diversity in Recommender Systems , 2015, Recommender Systems Handbook.

[35]  Tie-Yan Liu,et al.  A Theoretical Analysis of NDCG Type Ranking Measures , 2013, COLT.

[36]  Pasquale Lops,et al.  Semantics-aware Content-based Recommender Systems , 2014, CBRecSys@RecSys.

[37]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.