SIRUP: Serendipity In Recommendations via User Perceptions

In this paper, we propose a model to operationalise serendipity in content-based recommender systems. The model, called SIRUP, is inspired by the Silvia's curiosity theory, based on the fundamental theory of Berlyne, aims at (1) measuring the novelty of an item with respect to the user profile, and (2) assessing whether the user is able to manage such level of novelty (coping potential). The novelty of items is calculated with cosine similarities between items, using Linked Open Data paths. The coping potential of users is estimated by measuring the diversity of the items in the user profile. We deployed and evaluated the SIRUP model in a use case with TV recommender using BBC programs dataset. Results show that the SIRUP model allows us to identify serendipitous recommendations, and, at the same time, to have 71% precision.

[1]  M. Seligman,et al.  Character Strengths and Virtues: A Handbook and Classification , 2004 .

[2]  Pasquale Lops,et al.  Introducing Serendipity in a Content-Based Recommender System , 2008, 2008 Eighth International Conference on Hybrid Intelligent Systems.

[3]  G. Loewenstein.  The psychology of curiosity: A review and reinterpretation. , 1994 .

[4]  Wendy Hall,et al.  The Semantic Web Revisited , 2006, IEEE Intelligent Systems.

[5]  Dhavalkumar Thakker,et al.  Exploring exploratory search: a user study with linked semantic data , 2013, IESD '13.

[6]  Lora Aroyo,et al.  Using Linked Data to Diversify Search Results a Case Study in Cultural Heritage , 2014, EKAW.

[7]  Franca Garzotto,et al.  User effort vs. accuracy in rating-based elicitation , 2012, RecSys.

[8]  Eli Pariser,et al.  The Filter Bubble: What the Internet Is Hiding from You , 2011 .

[9]  Véronique Malaisé,et al.  Anchoring Dutch Cultural Heritage Thesauri to WordNet: Two Case Studies , 2007, LaTeCH@ACL 2007.

[10]  D. Hoang.  FLOW: The Psychology of Optimal Experience , 2018 .

[11]  Franca Garzotto,et al.  Investigating the Persuasion Potential of Recommender Systems from a Quality Perspective: An Empirical Study , 2012, TIIS.

[12]  Véronique Malaisé,et al.  Enriching a Thesaurus to Improve Retrieval of Audiovisual Documents , 2008, SAMT.

[13]  Pasquale Lops,et al.  Enhanced semantic TV-show representation for personalized electronic program guides , 2012, UMAP.

[14]  Aftab Iqbal.  Fostering Serendipity through Big Linked Data , 2013 .

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

[16]  P. Silvia.  Emotional Responses to Art: From Collation and Arousal to Cognition and Emotion , 2005 .

[17]  Tomas Vitvar,et al.  Personalised Access to Linked Data , 2014, EKAW.

[18]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[19]  Lora Aroyo,et al.  Crowdsourced Evaluation of Semantic Patterns for Recommendations , 2013 .

[20]  Takayuki Akiyama,et al.  Proposal and Evaluation of Serendipitous Recommendation Method Using General Unexpectedness , 2010, PRSAT@RecSys.

[21]  Fabien L. Gandon,et al.  Discovery hub: on-the-fly linked data exploratory search , 2013, I-SEMANTICS '13.

[22]  D. Berlyne.  Conflict, arousal, and curiosity , 2014 .

[23]  D. Berlyne.  A theory of human curiosity. , 1954, British journal of psychology.

[24]  P. Silvia.  Interest—The Curious Emotion , 2008 .

[25]  A. T. Schreiber,et al.  Searching and Annotating Virtual Heritage Collections with Semantic-Web Techniques , 2007 .

[26]  Alexandre Miguel Pinto,et al.  Enriching Electronic Programming Guides with Web Data , 2014 .

[27]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .

[28]  Rik Van de Walle,et al.  Effect of Heuristics on Serendipity in Path-Based Storytelling with Linked Data , 2016, HCI.

[29]  Harald Sack,et al.  Towards exploratory video search using linked data , 2009, 2009 11th IEEE International Symposium on Multimedia.

[30]  Lora Aroyo,et al.  Crowdsourced Evaluation of Semantic Patterns for Recommendation , 2013, UMAP Workshops.

[31]  Olaf Hartig,et al.  SPARQL for a Web of Linked Data: Semantics and Computability (Extended Version) , 2012, ESWC.

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