Challenges of Serendipity in Recommender Systems

Most recommender systems suggest items similar to a user profile, which results in boring recommendations limited by user preferences indicated in the system. To overcome this problem, recommender systems should suggest serendipitous items, which is a challenging task, as it is unclear what makes items serendipitous to a user and how to measure serendipity. The concept is difficult to investigate, as serendipity includes an emotional dimension and serendipitous encounters are very rare. In this paper, we discuss mentioned challenges, review definitions of serendipity and serendipity-oriented evaluation metrics. The goal of the paper is to guide and inspire future efforts on serendipity in recommender systems.

[1]  Panagiotis Adamopoulos,et al.  On Unexpectedness in Recommender Systems , 2013, ACM Trans. Intell. Syst. Technol..

[2]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[3]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[4]  Pasquale Lops,et al.  Can a Recommender System Induce Serendipitous Encounters , 2010 .

[5]  M. Kaminskas.  Measuring Surprise in Recommender Systems , 2014 .

[6]  Paolo Cremonesi,et al.  Tutorial on cross-domain recommender systems , 2014, RecSys '14.

[7]  E. Tacchini.  SERENDIPITOUS MENTORSHIP IN MUSIC RECOMMENDER SYSTEMS , 2012 .

[8]  Vikas Kumar,et al.  "I like to explore sometimes": Adapting to Dynamic User Novelty Preferences , 2015, RecSys.

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

[10]  Boi Faltings,et al.  Offline and online evaluation of news recommender systems at swissinfo.ch , 2014, RecSys '14.

[11]  Susan T. Dumais,et al.  Discovery is never by chance: designing for (un)serendipity , 2009, C&C '09.

[12]  Simon Colton,et al.  Modelling serendipity in a computational context , 2014, ArXiv.

[13]  Francesco Ricci,et al.  Contextual music information retrieval and recommendation: State of the art and challenges , 2012, Comput. Sci. Rev..

[14]  Anind K. Dey,et al.  Understanding and Using Context , 2001, Personal and Ubiquitous Computing.

[15]  Òscar Celma Herrada.  Music recommendation and discovery in the long tail , 2009 .

[16]  Pasquale Lops,et al.  An investigation on the serendipity problem in recommender systems , 2015, Inf. Process. Manag..

[17]  G. B. Parks.  Serendipity and the Three Princes: From the Peregrinaggio of 1557.Theodore G. Remer , 1968, Renaissance Quarterly.

[18]  Barry Smyth,et al.  Communities, Collaboration, and Recommender Systems in Personalized Web Search , 2011, Recommender Systems Handbook.

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

[20]  Nigel Ford,et al.  Serendipity and information seeking: an empirical study , 2003, J. Documentation.

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

[22]  Iván Cantador,et al.  Cross-domain recommender systems : A survey of the State of the Art , 2012 .

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

[24]  Ryohei Orihara,et al.  Metrics for Evaluating the Serendipity of Recommendation Lists , 2007, JSAI.

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

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

[27]  Horace Ho-Shing Ip,et al.  An Unexpectedness-Augmented Utility Model for Making Serendipitous Recommendation , 2015, ICDM.

[28]  Boi Faltings,et al.  Predicting Online Performance of News Recommender Systems Through Richer Evaluation Metrics , 2015, RecSys.

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