Turning Experience Products into Search Products: Making User Feedback Count

Online shopping sites are faced with a significant problem: When offering experience products, i.e., products that lack a helpful description in terms of easily accessible factual properties (e.g., wine, cigars, and movies), a lot of work and time needs to be invested to provide such information. Two very popular approaches are the introduction of sophisticated categorization systems (e.g., fruity, woody, and peppery for wines) along with manual product classification performed by experts and the addition of user feedback mechanisms (e.g., ratings or textual reviews). While user feedback typically is easy to collect, for purposes of product search, it cannot be used as easily as this is possible with a systematic categorization scheme. In this paper, we propose an effective method to automatically derive product classifications of high quality from many different kinds of user feedback. Our semi-supervised method combines advanced data extraction methods with state-of-the-art classification algorithms and only requires a small number of training examples to be created manually by experts. We prove the benefits of our approach by performing an extensive evaluation in the movie domain.

[1]  Zhihua Cai,et al.  Evaluation Measures of the Classification Performance of Imbalanced Data Sets , 2009 .

[2]  Chris H. Q. Ding,et al.  Low-order tensor decompositions for social tagging recommendation , 2011, WSDM '11.

[3]  Iryna Gurevych,et al.  Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations , 2009, TSA@CIKM.

[4]  R. Dholakia,et al.  Factors Driving Consumer Intention to Shop Online: An Empirical Investigation , 2003 .

[5]  Yongmin Li,et al.  Video classification using spatial-temporal features and PCA , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[6]  Wolf-Tilo Balke,et al.  Conceptual views for entity-centric search: turning data into meaningful concepts , 2012, Computer Science - Research and Development.

[7]  George Tzanetakis,et al.  Musical genre classification of audio signals , 2002, IEEE Trans. Speech Audio Process..

[8]  E. Hirschman,et al.  Hedonic Consumption: Emerging Concepts, Methods and Propositions , 1982 .

[9]  Patrick F. Reidy.  An Introduction to Latent Semantic Analysis , 2009 .

[10]  S. Erevelles.  Book Review: Re-Imagine: Business Excellence in a Disruptive Age: , 2006 .

[11]  William Nick Street,et al.  Collaborative filtering via euclidean embedding , 2010, RecSys '10.

[12]  Robert L. Goldstone,et al.  Concepts and Categorization , 2003 .

[13]  P. Gärdenfors.  Conceptual spaces as a framework for knowledge representation , 2004 .

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

[15]  Ying Liu,et al.  A survey of content-based image retrieval with high-level semantics , 2007, Pattern Recognit..

[16]  Domonkos Tikk,et al.  Recommending new movies: even a few ratings are more valuable than metadata , 2009, RecSys '09.

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

[18]  Dianhong Wang,et al.  Survey of Improving K-Nearest-Neighbor for Classification , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[19]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[20]  John Riedl,et al.  Navigating the tag genome , 2011, IUI '11.

[21]  Mike Thelwall,et al.  Synthesis Lectures on Information Concepts, Retrieval, and Services , 2009 .

[22]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[23]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[24]  Panagiotis Symeonidis,et al.  Tag recommendations based on tensor dimensionality reduction , 2008, RecSys '08.

[25]  P. Nelson.  Information and Consumer Behavior , 1970, Journal of Political Economy.

[26]  Wolf-Tilo Balke,et al.  Extracting Features from Ratings: The Role of Factor Models , 2011, ArXiv.

[27]  Lars Schmidt-Thieme,et al.  Tag-aware recommender systems by fusion of collaborative filtering algorithms , 2008, SAC '08.

[28]  Elizabeth Cooper-Martin,et al.  Consumers and Movies: Some Findings on Experiential Products , 1991 .

[29]  Shih-Fu Chang,et al.  A conceptual framework and empirical research for classifying visual descriptors , 2001, J. Assoc. Inf. Sci. Technol..

[30]  Lisa R. Klein.  Evaluating the Potential of Interactive Media through a New Lens: Search versus Experience Goods , 1998 .

[31]  Joann Peck,et al.  To have and to Hold: The Influence of Haptic Information on Product Judgments , 2003 .

[32]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[33]  Raymond R. Burke.  Technology and the customer interface: What consumers want in the physical and virtual store , 2002 .

[34]  Douglas Brown,et al.  Film Theory: An Introduction , 2013 .

[35]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[36]  Jiawei Han,et al.  Tensor space model for document analysis , 2006, SIGIR.

[37]  Makoto Nakayama,et al.  Has the web transformed experience goods into search goods? , 2010, Electron. Mark..

[38]  Bing Liu,et al.  Mining Opinion Features in Customer Reviews , 2004, AAAI.

[39]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[40]  D. Chandler.  An Introduction to Genre Theory , 2004 .

[41]  Yi Zhang,et al.  Efficient bayesian hierarchical user modeling for recommendation system , 2007, SIGIR.

[42]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..