A recommender system suggests items that might be interesting for the users, by
analyzing their previous preferences. While these preferences can be explicitly
expressed in the form of ratings or likes, the interactions of the users with the
system can also be exploited, in order to collect implicit preferences and provide
more fine-grained and objective knowledge on what the users are experiencing [
Therefore, the user interface engineering community can play a crucial role
in the design of more e↵ective recommender systems. Indeed, it is important to
move from the perception of a recommender system as a black box that provides
suggestions that are not interpretable and are completely disconnected from the
user model, since this would lead to a lack of trust of the users in the system [
Moreover, the possibility to allow the users to tailor the recommendations to their current needs is essential. This dynamical adaptation to the users can be pursued by o↵ering means to let a user express what she is currently interested in and is expecting from the system, or by inferring these needs by monitoring her interactions with it. Being able to control the user model, in order to discard outdated preferences or preferences that are related to other users (e.g., when a profile is used to buy a gift for another person) is another crucial aspect.
The user interface also plays a crucial role when visualizing or communicating risks in recommendation domains such as health and medicine.
In this regard, the user interface engineering community has the expertise for generalizing the existing approaches, and to elaborate new patterns and metaphors for supporting users in both inspecting and controlling Recommender Systems. The papers in this workshop proceedings volume present di↵erent results and ongoing research on the following topics: – Design patterns, metaphors, and innovative solutions for the end-user inspection and control of a Recommender System; – Case studies, applications, prototypes of innovative ways for considering the users’ interactions as data for Recommender Systems; – Position papers on problems and solutions for supporting the Recommender Systems through user interaction and the user while interacting with applications that exploit Recommender Systems; – Feature selection and data filtering approaches to extract information from the data gathered through Human-Computer Interaction techniques, for recommendation purposes; – Analysis of implicit data collected from real-world systems, in order to evaluate their e↵ectiveness for recommendation and personalization purposes.
The workshop was an event co-located with the 9th ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS 2017). After the review process, the programme committee selected 6 papers. In addition, Martijn C. Willemsen was invited to give a talk on understanding user preferences and goals in recommender systems. We thank all the authors for their submissions and all members of the program committee. We are grateful to the EICS workshop chairs Teresa Rom˜ao and Lucio Davide Spano for their support in the workshop organization.
The workshop was organized by the Digital Humanities unit at Eurecat (Spain) and by the Department of Mathematics and Computer Science at the University of Cagliari (Italy).
Workshop Organizers – Ludovico Boratto (Eurecat, Spain) – Salvatore Carta (University of Cagliari, Italy) – Gianni Fenu (University of Cagliari, Italy) Program Committee – Christine Bauer (Johannes Kepler University Linz, Austria) – Andr´e Calero Valdez (RWTH-Aachen University, Germany) – Li Chen (HKBU Faculty of Science, Hong Kong) – Ed H. Chi (Google Research, USA) – Maria Laura Clemente (CRS4, Italy) – Michael D. Ekstrand (Boise State University, USA) – Mehdi Elahi (Free University of Bozen-Bolzano, Italy) – Mark Graus (Eindhoven University of Technology, Netherlands) – Bart Knijnenburg (Clemson University, USA) – Tobias Ley (Tallinn University, Estonia) – John O’Donovan (University of California, Santa Barbara, USA) – Denis Parra (Pontificia Universidad Catolica de Chile, Chile) – Roberto Saia (University of Cagliari, Italy) – Olga C. Santos (UNED, Spain) – Giovanni Stilo (Sapienza University of Rome, Italy) – Wolfgang Woerndl (TU Mnchen, Germany) Understanding user preferences and goals in recommender systems . . . . . .
Martijn C. Willemsen Testing a Recommender System for Self-Actualization . . . . . . . . . . . . . . . . .
Daricia Wilkinson, Saadhika Sivakumar, Pratitee Sinha, Bart P.
Knijnenburg Towards a Design Space for Personalizing the Presentation of Recommendations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Catalin-Mihai Barbu, Ju¨rgen Ziegler A Framework for Comparing Interactive Route Planning Apps in Tourism
Sergejs Pugacs, Sven Helmer, Markus Zanker Towards Chatbots as Recommendation Interfaces . . . . . . . . . . . . . . . . . . . . .
Maurizio Atzori, Ludovico Boratto, Lucio Davide Spano