A hybrid recommendation method that combines forgotten items and non-content attributes

Sistemas de Recomendacao (SsR) desempenham um papel importante em diversas aplicacoes Web, ajudando os usuarios a encontrar seus itens favoritos em meio a um grande numero de opcoes. Dentre os varios desafios ainda em aberto inerentes a SsR, esta tese aborda o desafio de ampliar a descoberta de itens potencialmente relevantes para cada usuario. Neste sentido, exploramos duas limitacoes algoritmicas despercebidas na literatura. Primeiro, SsR falham em recuperar itens consumidos ha muito tempo que sao potencialmente relevantes para os usuarios atualmente. Em segundo lugar, SsR nao conseguem capturar toda a extensao na qual sinais implicitos de preferencias observadas no consumo passado se relacionam com preferencias observadas no consumo atual. Abordamos a primeira limitacao revisando o passado remoto de consumo de cada usuario e identificando um subconjunto de itens consumidos e esquecidos atualmente, mas ainda re-consumiveis (i.e., itens esquecidos re-consumiveis). Mitigamos a segunda limitacao modelando explicitamente um subconjunto de atributos derivados de dados de consumo e metadados (i.e., atributos nao baseados em conteudo). Finalmente, propusemos ForNonContent, um metodo hibrido que aborda ambas limitacoes simultaneamente. Alem de validar a existencia de tais limitacoes lgoritmicas, analises offline em quatro conjuntos de dados reais demonstraram que recomendar itens esquecidos re-consumiveis pode propiciar recomendacoes diversificadas e nao obvias. Verificamos tambem que os atributos nao baseados em conteudo podem aperfeicoar recomendacoes geradas por seis principais SsR. Ademais, identificamos uma natureza complementar entre as melhorias associadas a cada limitacao. Finalmente, avaliacoes com usuarios reais do sistema MovieLens demonstraram que usuarios apreciaram as recomendacoes geradas por ForNonContent. Em suma, este trabalho apontou uma nova e promissora direcao para melhorar a experiencia dos usuarios com SsR.

[1]  Gediminas Adomavicius,et al.  Incorporating contextual information in recommender systems using a multidimensional approach , 2005, TOIS.

[2]  Y. Song,et al.  A Survey of Music Recommendation Systems and Future Perspectives , 2012 .

[3]  Neil J. Hurley,et al.  What Have the Neighbours Ever Done for Us? A Collaborative Filtering Perspective , 2009, UMAP.

[4]  John Riedl,et al.  Recommender systems: from algorithms to user experience , 2012, User Modeling and User-Adapted Interaction.

[5]  Saul Vargas,et al.  Rank and relevance in novelty and diversity metrics for recommender systems , 2011, RecSys '11.

[6]  Loriene Roy,et al.  Content-based book recommending using learning for text categorization , 1999, DL '00.

[7]  Hedderik van Rijn,et al.  Personal Publication Assistant: Abstract recommendations by a cognitive model , 2010, Cognitive Systems Research.

[8]  Thore Graepel,et al.  Matchbox: large scale online bayesian recommendations , 2009, WWW '09.

[9]  John R. Anderson,et al.  Reflections of the Environment in Memory Form of the Memory Functions , 2022 .

[10]  J. Avery,et al.  The long tail. , 1995, Journal of the Tennessee Medical Association.

[11]  Jun Wang,et al.  Optimizing multiple objectives in collaborative filtering , 2010, RecSys '10.

[12]  John R. Anderson,et al.  Practice and Forgetting Effects on Vocabulary Memory: An Activation-Based Model of the Spacing Effect , 2005, Cogn. Sci..

[13]  Yehuda Koren,et al.  Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[14]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation , 1997, CACM.

[15]  Gerald Albaum,et al.  The Likert Scale Revisited , 1997 .

[16]  Li Chen,et al.  A user-centric evaluation framework for recommender systems , 2011, RecSys '11.

[17]  Raphaël Troncy,et al.  Hybrid event recommendation using linked data and user diversity , 2013, RecSys.

[18]  John R. Anderson.  How Can the Human Mind Occur in the Physical Universe , 2007 .

[19]  Junjie Yao,et al.  Challenging the Long Tail Recommendation , 2012, Proc. VLDB Endow..

[20]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[21]  M. Lipczak,et al.  Tag Recommendation for Folksonomies Oriented towards Individual Users , 2008 .

[22]  Tie-Yan Liu,et al.  Learning to Rank for Information Retrieval , 2011 .

[23]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[24]  Domonkos Tikk,et al.  Investigation of Various Matrix Factorization Methods for Large Recommender Systems , 2008, ICDM Workshops.

[25]  Mi Zhang,et al.  Avoiding monotony: improving the diversity of recommendation lists , 2008, RecSys '08.

[26]  S. Floyd,et al.  Adaptive Web , 1997 .

[27]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[28]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[29]  Taek-Soo Kim,et al.  A statistical model for user preference , 2005, IEEE Transactions on Knowledge and Data Engineering.

[30]  Paulo Villegas,et al.  Music recommendations with temporal context awareness , 2010, RecSys '10.

[31]  Gerhard Friedrich,et al.  Recommender Systems - An Introduction , 2010 .

[32]  Thierry Bertin-Mahieux,et al.  The Million Song Dataset , 2011, ISMIR.

[33]  Diego Fernández,et al.  Comparison of collaborative filtering algorithms , 2011, ACM Trans. Web.

[34]  V. Mirrokni,et al.  A recommender system based on local random walks and spectral methods , 2007, WebKDD/SNA-KDD '07.

[35]  John Riedl,et al.  Collaborative Filtering Recommender Systems , 2011, Found. Trends Hum. Comput. Interact..

[36]  A. Tuzhilin,et al.  Extending Recommender Systems : A Multidimensional Approach , 2001 .

[37]  Christian Lebiere,et al.  The dynamics of cognition: An ACT-R model of cognitive arithmetic , 1999, Kognitionswissenschaft.

[38]  Bart P. Knijnenburg,et al.  User-Centric Evaluation Framework for Multimedia Recommender Systems , 2009, UCMedia.

[39]  Yanchun Zhang,et al.  Modelling User Behaviour for Web Recommendation Using LDA Model , 2008, 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[40]  Daniele Quercia,et al.  Auralist: introducing serendipity into music recommendation , 2012, WSDM '12.

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

[42]  Rong Hu,et al.  Enhancing recommendation diversity with organization interfaces , 2011, IUI '11.

[43]  Xiaohong Jiang,et al.  Modeling user and item biases with Gaussian distribution for collaborative filtering , 2011, 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[44]  Wagner Meira,et al.  A Characterization Methodology of Evolutionary Behavior in Recommender Systems , 2018, WEBIST.

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

[46]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[47]  John Riedl,et al.  An Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms , 2002, Information Retrieval.

[48]  Bernardo A. Huberman,et al.  Usage patterns of collaborative tagging systems , 2006, J. Inf. Sci..

[49]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[50]  Sahin Albayrak,et al.  User-centric evaluation of a K-furthest neighbor collaborative filtering recommender algorithm , 2013, CSCW.

[51]  Alexander Tuzhilin,et al.  The long tail of recommender systems and how to leverage it , 2008, RecSys '08.

[52]  Diyi Yang,et al.  Local implicit feedback mining for music recommendation , 2012, RecSys.

[53]  John Riedl,et al.  Application of Dimensionality Reduction in Recommender System - A Case Study , 2000 .

[54]  Eric Horvitz,et al.  Social Choice Theory and Recommender Systems: Analysis of the Axiomatic Foundations of Collaborative Filtering , 2000, AAAI/IAAI.

[55]  Jie Zhou,et al.  Dynamic Personalized Recommendation on Sparse Data , 2013, IEEE Transactions on Knowledge and Data Engineering.

[56]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[57]  Arjen P. de Vries,et al.  The Magic Barrier of Recommender Systems - No Magic, Just Ratings , 2014, UMAP.

[58]  chris-anderson.  The Long Tail: How Endless Choice is Creating Unlimited Demand , 2007 .

[59]  George Karypis,et al.  Item-based top-N recommendation algorithms , 2004, TOIS.

[60]  Byeong Man Kim,et al.  Constructing User Profiles for Collaborative Recommender System , 2004, APWeb.

[61]  Michael J. Pazzani,et al.  User Modeling for Adaptive News Access , 2000, User Modeling and User-Adapted Interaction.

[62]  Jimeng Sun,et al.  Temporal recommendation on graphs via long- and short-term preference fusion , 2010, KDD.

[63]  Walter Nicholson,et al.  Microeconomic Theory : Basic Principles and Extensions. --2nd. ed , 1978 .

[64]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .

[65]  Robin D. Burke,et al.  Hybrid Recommender Systems: Survey and Experiments , 2002, User Modeling and User-Adapted Interaction.

[66]  Éric Gaussier,et al.  Toward a New Protocol to Evaluate Recommender Systems , 2012, RUE@RecSys.

[67]  Bart P. Knijnenburg,et al.  Explaining the user experience of recommender systems , 2012, User Modeling and User-Adapted Interaction.

[68]  Françoise Fessant,et al.  State-of-the-Art Recommender Systems , 2009 .

[69]  David McSherry,et al.  Diversity-Conscious Retrieval , 2002, ECCBR.

[70]  Xiaohui Li,et al.  Multidimensional clustering based collaborative filtering approach for diversified recommendation , 2012, 2012 7th International Conference on Computer Science & Education (ICCSE).

[71]  Alan Hanjalic,et al.  List-wise learning to rank with matrix factorization for collaborative filtering , 2010, RecSys '10.

[72]  Noriaki Kawamae,et al.  Serendipitous recommendations via innovators , 2010, SIGIR.

[73]  Wagner Meira,et al.  Exploiting non-content preference attributes through hybrid recommendation method , 2013, RecSys.

[74]  Xinlong Bao,et al.  Stacking recommendation engines with additional meta-features , 2009, RecSys '09.

[75]  Xue Li,et al.  Time weight collaborative filtering , 2005, CIKM '05.

[76]  Hans-Peter Kriegel,et al.  Ieee Transactions on Knowledge and Data Engineering Probabilistic Memory-based Collaborative Filtering , 2022 .

[77]  Barry Smyth,et al.  On the Role of Diversity in Conversational Recommender Systems , 2003, ICCBR.

[78]  John Riedl,et al.  Is seeing believing?: how recommender system interfaces affect users' opinions , 2003, CHI '03.

[79]  Klaus J. Miescke,et al.  Statistical decision theory : estimation, testing, and selection , 2008 .

[80]  L. Maanen.  Recommender Systems for Literature Selection : A Competition between Decision Making and Memory Models , 2009 .

[81]  Roberto Turrin,et al.  Controlling Consistency in Top-N Recommender Systems , 2010, 2010 IEEE International Conference on Data Mining Workshops.

[82]  Manuel A. Sánchez-Montañés,et al.  Towards a more realistic evaluation: testing the ability to predict future tastes of matrix factorization-based recommenders , 2011, RecSys '11.

[83]  Adriano Veloso,et al.  Pareto-efficient hybridization for multi-objective recommender systems , 2012, RecSys.

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

[85]  Michael J. Pazzani,et al.  Learning Collaborative Information Filters , 1998, ICML.

[86]  Keiichiro Hoashi,et al.  Personalization of user profiles for content-based music retrieval based on relevance feedback , 2003, ACM Multimedia.

[87]  Kartik Hosanagar,et al.  Recommender systems and their impact on sales diversity , 2007, EC '07.

[88]  Dunja Mladenic,et al.  From Web to Social Web: Discovering and Deploying User and Content Profiles, Workshop on Web Mining, WebMine 2006, Berlin, Germany, September 18, 2006. Revised Selected and Invited Papers , 2007, WebMine.

[89]  Paul Resnick,et al.  Recommender systems , 1997, CACM.

[90]  Licia Capra,et al.  Temporal diversity in recommender systems , 2010, SIGIR.

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

[92]  Ulrich Güntzer,et al.  Algorithms for association rule mining — a general survey and comparison , 2000, SKDD.

[93]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[94]  Chhavi Rana,et al.  A study of the dynamic features of recommender systems , 2012, Artificial Intelligence Review.

[95]  William W. Cohen,et al.  Recommendation as Classification: Using Social and Content-Based Information in Recommendation , 1998, AAAI/IAAI.

[96]  Pasquale Lops,et al.  Content-based Recommender Systems: State of the Art and Trends , 2011, Recommender Systems Handbook.

[97]  Gediminas Adomavicius,et al.  Stability of Recommendation Algorithms , 2012, TOIS.

[98]  Anh Duc Duong,et al.  Addressing cold-start problem in recommendation systems , 2008, ICUIMC '08.

[99]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[100]  Neal Kiritkumar Lathia,et al.  Evaluating collaborative filtering over time , 2009, SIGIR 2009.

[101]  Philip S. Yu,et al.  GraphScope: parameter-free mining of large time-evolving graphs , 2007, KDD '07.

[102]  Tiejun Li,et al.  A modified fuzzy C-means algorithm for collaborative filtering , 2008, NETFLIX '08.

[103]  J R Anderson,et al.  Practice and retention: a unifying analysis. , 1999, Journal of experimental psychology. Learning, memory, and cognition.

[104]  Thomas Hofmann,et al.  Latent semantic models for collaborative filtering , 2004, TOIS.

[105]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[106]  Wagner Meira,et al.  The Oblivion Problem: Exploiting Forgotten Items to Improve Recommendation Diversity , 2011, DiveRS@RecSys.

[107]  Byron J. Gao,et al.  Learning to rank for hybrid recommendation , 2012, CIKM.

[108]  Lars Schmidt-Thieme,et al.  MyMediaLite: a free recommender system library , 2011, RecSys '11.

[109]  Klaas Bosteels,et al.  Music Recommendation and the Long Tail , 2010 .

[110]  B. Schwartz.  The Paradox of Choice: Why More Is Less , 2004 .

[111]  Mouzhi Ge,et al.  Beyond accuracy: evaluating recommender systems by coverage and serendipity , 2010, RecSys '10.

[112]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.