5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS) 2018 Vancouver, Canada, October 7th, 2018 Proceedings edited by Peter Brusilovsky Marco de Gemmis Alexander Felfernig Pasquale Lops John O’Donovan Giovanni Semeraro Martijn C. Willemsen in conjunction with 12th ACM Conference on Recommender Systems (RecSys 2018) © 2018. Copyright for the individual papers remains with the authors. Copying permitted for private and academic purposes. This volume is published and copyrighted by its editors. ii Preface This volume contains the papers presented at the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS), held as part of the 12th ACM Conference on Recommender System (RecSys), in Vancouver, Canada. RecSys is the premier international forum for the presentation of new research results, systems and techniques in the broad field of recommender systems. Recommendation is a particular form of information filtering, that exploits past behaviors and user similarities to generate a list of information items that is personally tailored to an end-user’s preferences. Since the emergence of recommender systems, a large majority of research focuses on objective accuracy criteria and less attention has been paid to how users interact with the system and the efficacy of interface designs from users’ perspectives. The field has reached a point where it is ready to look beyond algorithms, into users’ interactions, decision making processes, and overall experience. The IntRS workshop focuses on human-centered recommender system design and application. The workshop goal is to improve users’ overall experience with recommender systems by integrating different theories of human decision making into the construction of recommender systems and exploring better interfaces for recommender systems. The workshop follows successful workshops on the same topic organized at RecSys conferences in 2014 – 2017. The continuous aim of the workshop is to bring together researchers and practitioners around the topics of designing and evaluating novel intelligent interfaces for recommender systems in order to: (1) share research and techniques, including new design technologies and evaluation methodologies, (2) identify next key challenges in the area, and (3) identify emerging topics. The 11 technical papers included in the proceedings were selected through a rigorous reviewing process, where each paper was reviewed by three PC members. These papers cover the themes of Affective Factors, Novelty and Diversity, Decision Making and Visualization, Transparency and Explanations. The workshop additionally consists of an invited talk by Katrien Verbert on “Mixed-initiative Recommender Systems: Towards a Next Generation of Recommender Systems through User Involvement”. The IntRS chairs would like to thank the RecSys workshop chairs, Martha Larson and Alejandro Bellogin, for their guidance during the workshop organization. We also wish to thank all authors and all presenters, and the members of the program committee. All of them secured the workshop’s high quality standards. September 2018 Peter Brusilovsky Marco de Gemmis Alexander Felfernig Pasquale Lops John O’Donovan Giovanni Semeraro Martijn C. Willemsen iii iv IntRS 2018 Workshop Organization Chairs: Peter Brusilovsky, School of Information Sciences, University of Pittsburgh, USA Marco de Gemmis, Dept. of Computer Science, University of Bari Aldo Moro, Italy Alexander Felfernig, Institute for Software Technology, Graz University of Technology, Austria Pasquale Lops, Dept. of Computer Science, University of Bari Aldo Moro, Italy John O’Donovan, Dept. of Computer Science, Univ. of California, Santa Barbara, USA Giovanni Semeraro, Dept. of Computer Science, University of Bari Aldo Moro, Italy Martijn C. Willemsen, Eindhoven University of Technology, The Netherlands Proceedings Chair: Marco de Gemmis, Dept. of Computer Science, University of Bari Aldo Moro, Italy Web Chair: Pasquale Lops, Dept. of Computer Science, University of Bari Aldo Moro, Italy Program Committee: Robin Burke, DePaul University Li Chen, Hong Kong Baptist University Jaegul Choo, Korea University Michael Ekstrand, Boise State University Gerhard Friedrich, Alpen-Adria-Universitaet Klagenfurt Sergiu Gordea, Austrian Institute of Technology Denis Helic, KTI, TU Graz Dietmar Jannach, TU Dortmund Bart Knijnenburg, Clemson University Cataldo Musto, University of Bari Aldo Moro Fedelucio Narducci, University of Bari Aldo Moro Stefan Reiterer, TU Graz Olga C. Santos, aDeNu Research Group (UNED) Christin Seifert, University of Twente Luis Terán, University of Fribourg Marko Tkalčič, Free University of Bozen-Bolzano Markus Zanker, Free University of Bozen-Bolzano v vi Table of Contents Invited Talk Mixed-initiative Recommender Systems: Towards a Next Generation of Recommender 1 Systems through User Involvement Katrien Verbert Affective Factors Affective Computing and Bandits: Capturing Context in Cold Start Situations 2 Sebastian Oehme and Linus W. Dietz Novelty and Diversity A Diversity Adjusting Strategy with Personality for Music Recommendation 7 Feng Lu and Nava Tintarev Risk "Attention" or "Adventure": A Qualitative Study of Novelty and Familiarity in Music 15 Listening Vikas Kumar, Sabirat Rubya, Joseph A. Konstan and Loren Terveen MovieTweeters: An Interactive Interface to Improve Recommendation Novelty 24 Ishan Ghanmode and Nava Tintarev Decision Making and Visualization Analysis of User Behavior in Interfaces with Recommended Items: An Eye-tracking 32 Study Peter Gaspar, Michal Kompan, Jakub Simko and Maria Bielikova From Recommendation to Curation: When the System Becomes your Personal Docent 37 Nevena Dragovic, Ion Madrazo Azpiazu and Maria Soledad Pera Online Daters’ Willingness to Use Recommender Technology for Mate Selection 45 Decisions Stephanie Tom Tong, Elena F. Corriero, Robert G. Matheny and Jeffrey T. Hancock Using Visualizations to Encourage Blind-Spot Exploration 53 Jayachithra Kumar and Nava Tintarev vii Transparency and Explanations Assessing the Value of Transparency in Recommender Systems: An End-User 61 Perspective Eric S. Vorm and Andrew D. Miller Towards Explanations for Visual Recommender Systems of Artistic Images 69 Vicente Domínguez, Pablo Messina, Christoph Trattner and Denis Parra Understanding how to Explain Package Recommendations in the Clothes Domain 74 Agung Toto Wibowo, Advaith Siddharthan, Judith Masthoff and Chenghua Lin viii