Evaluación de interfaces de explicación en los sistemas de recomendación
Evaluation of Explanation Interfaces in Recommender Systems
Resumen (es_ES)
Las interfaces de explicación se tornan una herramienta útil para los sistemas con una alta cantidad de contenido a ser evaluado por los usuarios. Las diferentes interfaces representan una ayuda para los usuarios indecisos o aquellos que consideran los sistemas una caja cerrada inteligente. Estos sistemas muestran recomendaciones a los usuarios basados en diferentes modelos. En el presente trabajo se presentan los diferentes objetivos perseguidos con las interfaces y algunos de los criterios que pudieran ser analizados, así como una propuesta de métricas para registrar resultados. Se muestran finalmente los principales resultados de un estudio con usuarios reales y su interacción con sistemas de uso cotidiano. Dentro de las principales conclusiones destaca el impacto positivo en relación al tiempo de interacción con los aplicativos y la aceptación de las recomendaciones recibidas.Resumen (en_US)
Explaining interfaces become a useful tool in systems that have a lot of content to evaluate by users. The different interfaces represent a help for the undecided users or those who consider systems as boxed black smart. These systems present recommendations to users based on different learning models. In this paper, we present the different objectives of the explanation interfaces and some of the criteria that you can evaluate, as well as a proposal of metrics to obtain results in the experiments. Finally, we showed the main results of a study with real users and their interaction with e-commerce systems. Among the main results, highlight the positive impact in relation to the time of interaction with the applications and acceptance of the recommendations received.
Descargas
Referencias
Avazpour, I.; Pitakrat, T.; Grunske, L. y Grundy, J. (2014) Dimensions and Metrics for Evaluating Recommendation Systems. Recommendation Systems in Software Engineering. 29 pp.
Ben-Elazar S. y Koenigstein, N. (2014) A Hybrid Explanations Framework for Collaborative Filtering Recommender Systems. RecSys Posters
Bridge, D. y Dunleavy, K. (2014) If you liked Herlocker et al.'s explanations paper, then you might like this paper too, in Nava Tintarev, John O'Donovan, Peter Brusilovsky, Alexander Felfernig, Giovanni Semeraro and Pasquale Lops (eds.), Procs. of the Workshop on Interfaces and Human Decision Making for Recommender Systems (Worskhop Programme of the Eighth ACM Conference on Recommender Systems), pp.22-27
Chen L. y Pu, P. (2005) Trust building in recommender agents. In in 1st International Workshop on Web Personalization, Recommender Systems and Intelligent User Interfaces (WPRSIUI05), pages 135–145
Herlocker, J. L.; Konstan, J. A.; y Riedl, J. (2000) Explaining collaborative filtering recommendations. In CSCW ’00: Proceedings of the 2000 ACM Conference on Computer Supported Cooperative Work, pages 241–250, New York, NY, USA. Association for Computing Machinery
Lacave, C. y Diez, F. J. (2004) A review of explanation methods for heuristic expert systems. The Knowledge Engineering Review, 19(02): pp 133–146
Pazzani, M.J. y Billsus, D. (2007) Content-based recommendation systems. In: The Adaptive Web: Methods and Strategies of Web Personalization, chap. 10, pp. 325–341
Pu P. y Chen, L. (2006) Trust building with explanation interfaces. In Proceeding of the 11th international conference on Intelligent User Interfaces, IUI ’06, pp 93–100. Association for Computing Machinery Press
Pu P. y Chen, L. (2007) Trust-inspiring explanation interfaces for recommender systems. Knowledge-Based Systems, 20(6): pp 542–556
Tintarev, N. y Masthoff, J. (2007) A survey of explanations in recommender systems. In: Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering Workshop. pp. 801–810. IEEE Computer Society, Washington, DC, USA 2007
Tintarev, N. y Masthoff, J. (2011) Designing and evaluating explanations for recommender systems. In: Recommender Systems Handbook, pp. 479–510
Zanker, M. y Schoberegger, M. (2014) An Empirical Study on the Persuasiveness of Fact-based Explanations for Recommender Systems. In Proceedings IntRS Workshop, 2014, pp 33-36
Zhang, Y. (2014) Browser-Oriented Universal Cross-Site Recommendation and Explanation based on User Browsing Logs. In Proceedings of the 8th ACM Conference Series on Recommender Systems (RecSys 2014), Oct. 6 - 10, 2014, Foster City, Silicon Valley, USA
Zhang, Y.; Lai, G.; Zhang, M.; Zhang, Y.; Liu, Y. y Ma, S. (2014) Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. SIGIR 2014: pp 83-92
Derechos de autor 2017 Revista Científica

Esta obra está bajo licencia internacional Creative Commons Reconocimiento 4.0.