Introducción
Las técnicas utilizadas en la exploración de grandes colecciones de productos, tales como libros (e.g. librarything.com), películas (e.g. netflix.com), fotos (e.g. flickr.com), artículos científicos (e.g. citeulike.com), web bookmarks (e.g. del.icio.us), etc., se construyen a partir de la investigación en artefactos colaborativos que permitan que el conocimiento, de ciertos individuos acerca de ciertos ítems, se propague a otros, siendo su objetivo generar una inteligencia colaborativa que permita guiar a los usuarios en búsquedas, personalizándolas hacia sus gustos, alejándolo de sus preferencias negativas. De esta forma se logra una experiencia de exploración que elimina la frustración que genera el recorrer inmensas colecciones de productos sin descubrir nada nuevo o interesante.
Los métodos tradicionales de recomendación y también los más precisos construyen perfiles de usuarios, basados en su historial de navegación o basados en evaluaciones explícitas de los productos. A partir de estas evaluaciones, el sistema infiere un conjunto común de características, en un espacio abstracto, que comparten el producto y el usuario, con lo cual se minimiza el error de predicción del conjunto de datos de entrenamiento.
En otras palabras, la evaluación es equivalente a la medida de afinidad entre el vector usuario y el vector producto definido en este espacio abstracto. Este método logra capturar así las interrelaciones entre usuarios y productos, de modo que permite predecir la evaluación que un usuario dará a un producto a partir de sus evaluaciones pasadas y de las evaluaciones que usuarios similares han hecho de este producto.
Bell R.M., Koren Y., & C, V. (2007). The BellKor solution to the Net Flix Prize. Technical Report, AT&T Labs Research. doi: http://www.netflixprize.com/assets/ProgressPrize2007_KorBell.pdf
Byrd, R. H., Lu, P., Nocedal, J., & Zhu, C. (1995). A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comput., 16(5), 1190-1208. doi:10.1137/0916069
Fellbaum, C. (1998). WordNet An Electronic Lexical Database. Cambridge, MA ; London: The MIT Press. Retrieved from http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=8106
Jones, K. S. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28, 11-21.
Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix Factorization Techniques for Recommender Systems. Computer, 42(8), 30-37. doi:10.1109/MC.2009.263
Lops, P., Gemmis, M., & Semeraro, G. (2011). Content-based Recommender Systems: State of the Art and Trends. In F. Ricci, L. Rokach, B. Shapira, & P.B. Kantor (Eds.), Recommender Systems Handbook (pp. 73-105). Springer US. Retrieved from http://dx.doi.org/10.1007/978-0-387-85820-3_3
Lops, P., Gemmis, M., Semeraro, G., Musto, C., Narducci, F., & Bux, M. (2009). A Semantic Content-Based Recommender System Integrating Folksonomies for Personalized Access. In G. Castellano, L. Jain, & A. Fanelli (Eds.), Web Personalization in Intelligent Environments (Vol. 229, pp. 27-47). Springer Berlin Heidelberg. Retrieved from http://dx.doi.org/10.1007/978-3-642-02794-9_2.
Penrose, R., & Todd, J. A. (n.d.). On best approximate solutions of linear matrix equations. Mathematical Proceedings of the Cambridge Philosophical Society, null(01), 17-19. doi:10.1017/S0305004100030929
Robertson, S. (2005). How Okapi Came to TREC. In E. M. Voorhees & D. K. Harman, TREC: Experiment in Information Retrieval (pp. 287-300). MIT Press.
Salton, G., Wong, A. K. C., & Yang, C.-S. (1975). A vector space model for automatic indexing. Commun. ACM, 18(11), 613-620.
Schein, A., Pennock, D., & Ungar. (2002). Methods and metrics for cold-start recommendations. In SIGIR (pp 253-260). New York, NY, USA: ACM
Sen, S., Harper, F. M., LaPitz, A., & Riedl, J. (2007). The quest for quality tags. In Proceedings of the 2007 International ACM Conference on Supporting Group Work (pp. 361-370). New York, NY, USA: ACM.
Smola, A. J., & Schölkopf, B. (1998). A Tutorial on Support Vector Regression. Royal Holloway College, London, U.K., NeuroCOLT Tech. Rep. TR 1998-030, 1998.
Vanegas, J. A., Caicedo, J. C., Camargo, J. E., & Ramos-Pollán, R. (2012). Bioingenium at Image. CLEF 2012: Textual and Visual Indexing for Medical Images. In CLEF (Online Working Notes/Labs/Workshop). Rome, Italy.
Vig, Jesse, Sen, S., & Riedl, J. (2012). The Tag Genome: Encoding Community Knowledge to Support Novel Interaction. ACM Transactions on Interactive Inteligent Systems, 2(3). (pp 13:1-13:44)
Zhang, Z.-K., Zhou, T., & Zhang, Y.-C. (2011). Tag-Aware Recommender Systems: A State-of-the-Art Survey. Journal of Computer Science and Technology, 26(5), 767-777. doi:10.1007/s11390-011-0176-1
Zipf, G. K. (1950). Human behavior and the principle of least effort. Journal of Clinical Psychology, Adisson Wesley, 6(3). doi:10.1002/1097-4679(195007)6:3 <306::AID-JCLP2270060331>3.0.CO;2-7
You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer
Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer
Copyright Universidad Distrital Francisco José de Caldas, Facultad Tecnológica Sep 2015
Abstract
Recommender systems allow users to have a personalized view of large sets of products, relieving the overload problem of choice in e-commerce sites. Usually, recommendations are obtained using the technique called "collaborative filtering". This technique filters the products the users wish, from those they don´t want, inferring affinities between products and users in a space of abstract features, also called a latent space. These techniques have proven to be of great predictive value, but these created profiles are neither understandable, nor editable for users, enclosing users in a bubble, in which they only receive collaborative recommendations conditioned by their historcal behaviors. In our work we propose a method to build user profiles, defined in interpretable spaces, or defined in terms of collaborative tags or keywords (i.e. words extracted from the descriptions of the product), which can be interpreted and modified by users. The model proposed generate linear profiles, whose coefficients, positive or negative, reflect the user's affinity towards tags or keywords, according to the space selected. To test our hypothesis, we used the dataset of research in movie recommender systems from the University of Minnesota: Movielens. The results show that the predictive ability of the model, based on interpretable user profiles, is comparable to those mdels based on abstract profiles with the added benefit that these profiles are interpretable.
You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer
Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer