Inferring Networks of Substitutable and Complementary Products

To design a useful recommender system, it is important to understand how products relate to each other. For example, while a user is browsing mobile phones, it might make sense to recommend other phones, but once they buy a phone, we might instead want to recommend batteries, cases, or chargers. In economics, these two types of recommendations are referred to as substitutes and complements: substitutes are products that can be purchased instead of each other, while complements are products that can be purchased in addition to each other. Such relationships are essential as they help us to identify items that are relevant to a user's search. Our goal in this paper is to learn the semantics of substitutes and complements from the text of online reviews. We treat this as a supervised learning problem, trained using networks of products derived from browsing and co-purchasing logs. Methodologically, we build topic models that are trained to automatically discover topics from product reviews that are successful at predicting and explaining such relationships. Experimentally, we evaluate our system on the Amazon product catalog, a large dataset consisting of 9 million products, 237 million links, and 144 million reviews.

[1]  J. Nocedal.  Updating Quasi-Newton Matrices With Limited Storage , 1980 .

[2]  A. Mas-Colell,et al.  Microeconomic Theory , 1995 .

[3]  Ilya Segal,et al.  Solutions manual for Microeconomic theory : Mas-Colell, Whinston and Green , 1997 .

[4]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[5]  David M. Pennock,et al.  Methods and metrics for cold-start recommendations , 2002, SIGIR '02.

[6]  Thomas L. Griffiths,et al.  Hierarchical Topic Models and the Nested Chinese Restaurant Process , 2003, NIPS.

[7]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

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

[9]  Eric K. Ringger,et al.  Pulse: Mining Customer Opinions from Free Text , 2005, IDA.

[10]  Oren Etzioni,et al.  Extracting Product Features and Opinions from Reviews , 2005, HLT.

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

[12]  David M. Blei,et al.  Supervised Topic Models , 2007, NIPS.

[13]  Ivan Titov,et al.  A Joint Model of Text and Aspect Ratings for Sentiment Summarization , 2008, ACL.

[14]  Ivan Titov,et al.  Modeling online reviews with multi-grain topic models , 2008, WWW.

[15]  Junyu Niu,et al.  Substitutes or complements: another step forward in recommendations , 2009, EC '09.

[16]  David M. Blei,et al.  Connections between the lines: augmenting social networks with text , 2009, KDD.

[17]  Amélie Marian,et al.  Beyond the Stars: Improving Rating Predictions using Review Text Content , 2009, WebDB.

[18]  Wei Chu,et al.  Information Services]: Web-based services , 2022 .

[19]  Chenglei Yang,et al.  On centroidal voronoi tessellation—energy smoothness and fast computation , 2009, TOGS.

[20]  David M. Blei,et al.  Relational Topic Models for Document Networks , 2009, AISTATS.

[21]  Yan Liu,et al.  Topic-link LDA: joint models of topic and author community , 2009, ICML '09.

[22]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[23]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[24]  Noémie Elhadad,et al.  An Unsupervised Aspect-Sentiment Model for Online Reviews , 2010, NAACL.

[25]  Sreenivas Gollapudi,et al.  Shopping for products you don't know you need , 2011, WSDM '11.

[26]  Shuang-Hong Yang,et al.  Functional matrix factorizations for cold-start recommendation , 2011, SIGIR.

[27]  Yehuda Koren,et al.  Advances in Collaborative Filtering , 2011, Recommender Systems Handbook.

[28]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[29]  William W. Cohen,et al.  Block-LDA: Jointly Modeling Entity-Annotated Text and Entity-Entity Links , 2014, Handbook of Mixed Membership Models and Their Applications.

[30]  Sreenivas Gollapudi,et al.  Result enrichment in commerce search using browse trails , 2011, WSDM '11.

[31]  Padhraic Smyth,et al.  Dynamic Egocentric Models for Citation Networks , 2011, ICML.

[32]  Paolo Rosso,et al.  Mining Subjective Knowledge from Customer Reviews: A Specific Case of Irony Detection , 2011, WASSA@ACL.

[33]  Martin Ester,et al.  On the design of LDA models for aspect-based opinion mining , 2012, CIKM.

[34]  Vanja Josifovski,et al.  Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior , 2012, Proc. VLDB Endow..

[35]  Christophe Diot,et al.  Finding a needle in a haystack of reviews: cold start context-based hotel recommender system , 2012, RecSys.

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

[37]  Martin Ester,et al.  The FLDA model for aspect-based opinion mining: addressing the cold start problem , 2013, WWW.

[38]  William W. Cohen,et al.  Block-LDA: Jointly Modeling Entity-Annotated Text and Entity-Entity Links , 2014, Handbook of Mixed Membership Models and Their Applications.