Preface (Decisions@RecSys’11) Interacting with a recommender system means to take different decisions such as selecting a song/movie from a recommendation list, selecting specific feature values (e.g., camera’s size, zoom) as criteria, selecting feedback features to be critiqued in a critiquing based recommendation session, or selecting a repair proposal for inconsistent user preferences when interacting with a knowledge based recommender. In all these scenarios, users have to solve a decision task. The major focus of this workshop (Decisions@RecSys’11) are approaches for efficient human decision making in different recommendation scenarios. The complexity of decision tasks, limited cognitive resources of users, and the tendency to keep the overall decision effort as low as possible leads to the phenomenon of bounded rationality, i.e., users are exploiting decision heuristics rather than trying to take an optimal decision. Furthermore, preferences of users will likely change throughout a recommendation session, i.e., preferences are constructed in a specific decision environment and users do not know their preferences beforehand.
Decision making under bounded rationality is a door opener for different types of non conscious influences on the decision behavior of a user. Theories from decision psychology and cognitive psychology are trying to explain these influences, for example, decoy effects and defaults can trigger significant shifts in item selection probabilities; in group decision scenarios, the visibility of the preferences of other group members can have a significant impact on the final group decision.
The major goal of this workshop is (was) to establish a platform for industry and academia to present and discuss new ideas and research results that are related to human decision making in recommender systems. The workshop consists (consisted) of technical sessions in which results of ongoing research are (were) presented, informal group discussions on focused topics, and a keynote talk given by Anthony Jameson from DFKI, Germany. The topics of papers submitted to the workshop can be summarized as follows: Decision heuristics: the role of decision heuristics/phenomena (e.g., decoys and anchoring) in the construction of recommender applications.
Recommender user interfaces: impact of recommender interfaces on human decision making behavior.
Group decision making: group recommendation algorithms and group decision strategies.
Emotion based recommendation: emotion detection and emotion aware recommender applications.
New application domains: smart homes and intelligent data management.
The workshop material (list of accepted papers, invited talk, and the workshop schedule) can be found at the Decisions@RecSys 2011 workshop webpage: recex.ist.tugraz.at/RecSysWorkshop. Alexander Felfernig, Li Chen, and Monika Mandl October 2011 Research on ”Human Recommender Interaction” is scarce. Algorithm optimization and off line testing using measures like RMSE are dominant topics in the RecSys community, but theorizing about consumer decision processes and measuring user satisfaction in online tests is less common. Researchers in Marketing and Decision Making have been investigating consumer choice processes in great detail, but only sparingly put this knowledge to use in technological applications. Human Computer Interaction has been focusing on the usability of interfaces for ages, but does not seem to link research on consumer choice and recommender system interfaces.
keynote speeches, 7 accepted papers and a lively panel discussion introduced the visitors of
hope to further strengthen the bonds between these researchers, to exchange new experiences, and meet other new researchers working on user centric research in
Panel description:
This algorithm is better than others along a particular dimension (e.g., diversity, novelty) This way of eliciting ratings leads to greater accuracy of recommendations This recommender system (algorithm, interface, etc.) is preferred by users This recommender system (algorithm, interface, etc.) leads to greater long term user retention than other systems For each of these claims recommender systems researchers and practitioners have developed several distinct metrics to evaluate them, as well as a diverse set of procedures to conduct the evaluation. This apparent heterogeneity stands in the way of scientific progress. Researchers face the impossible challenge of selecting a subset of claims/metrics/procedures that allows for comparability of their work with previous studies. To create a rigorous, cumulative science of recommender systems, we need to take a step back and reflect on our current practices.
This reflection is partly philosophical: Which of the possible investigative claims are worthy of our consideration? The answer to this question depends on the purpose or goal we ascribe to a recommender system, whom we feel should benefit from it, and where we believe the field of recommender systems blends into other fields. In other words, we need to decide on what a ”good recommender system” really is.
It is also partly practical: As scientists, we need to understand best practices for providing the evidence to back up these claims, and for providing such evidence in a way that allows our field to move forward. Some claims (e.g., novelty) can simply be supported by a review of related work. Others (e.g., user satisfaction) require careful experimental designs that isolate and make salient as much as possible the factor being studied so that differences in results can be attributed to that factor. Still others (e.g., algorithmic performance) require standardization of metrics and evaluation procedures to ensure apples to apples comparisons against the best prior work.
This panel will address the general challenge of building a rigorous, cumulative science out of recommender systems with a specific focus on experiment design and standardization in support of better user centered evaluation.
October 2011 Workshop Committee (Decisions@RecSys’11)
Alexander Felfernig, Graz University of Technology Li Chen, Hong Kong Baptist University
Monika Mandl, Graz University of Technology
Mathias Bauer, Mineway, Germany Shlomo Berkovsky, CSIRO, Australia Robin Burke, De Paul University, USA Li Chen, Hong Kong Baptist University, China Hendrik Drachsler, Open University of the Netherlands Alexander Felfernig, Graz University of Technology, Austria Gerhard Friedrich, University of Klagenfurt, Austria Sergiu Gordea, Austrian Institute for Technology, Austria Mehmet Goker, Salesforce, USA Andreas Holzinger, Medical University Graz, Austria Dietmar Jannach, University of Dortmund, Germany Alfred Kobsa, University of California, USA Gerhard Leitner, University of Klagenfurt, Austria Walid Maalej, Technische Universität München, Germany Monika Mandl, Graz University of Technology, Austria Francisco Martin, BigML, USA Alexandros Nanopoulos, University of Hildesheim, Germany Francesco Ricci, University of Bolzano, Italy Olga Santos, UNED, Spain Monika Schubert, Graz University of Technology, Austria Markus Strohmaier, Graz University of Technology, Austria Erich Teppan, University of Klagenfurt, Austria Nava Tintarev, University of Aberdeen, UK Marc Torrens, Strands, Spain Alex Tuzhilin, New York University, USA Markus Zanker, University of Klagenfurt, Austria Christoph Zehentner, Graz University of Technology, Austria
Ge Mouzhi, University of Dortmund, Germany Workshop Committee (UCERSTI) Organization Martijn Willemsen, Human Technology Interaction, Eindhoven University of Technology, Netherlands Dirk Bollen, Human Technology Interaction, Eindhoven University of Technology, Netherlands Michael Ekstrand, GroupLens Research, Department of Computer Science and Engineering University of Minnesota, USA Program Committee Benedict G. C. Dellaert, Department of Business Economics, Erasmus University Rotterdam, The Netherlands Maciej Dabrowski, Digital Enterprise Research Institute, National University of Ireland, Galway, Ireland Alexander Felfernig, Software Technology Institute, Graz University of Technology, Germany David Geerts, Centre for User Experience Research, University of Leuven, Belgium Kristiina Karvonen, Helsinki Institute for Information Technology HIIT, Aalto, Finland Alfred Kobsa, Donald Bren School of Information and Computer Sciences, University of California, Irvine, USA Bart Knijnenburg, Donald Bren School of Information and Computer Sciences, University of California, Irvine, USA Artus Krohn Grimberghe, Information Systems and Machine Learning Lab, University of Hildesheim, Germany Sean M. McNee, FTI Technology, USA Steffen Rendle, Steffen Rendle, Social Network Analysis, University of Konstanz, Germany Sylvain Senecal, Department of Marketing, HEC Montreal, Canada Decoy Effects in Financial Service E Sales Systems E. Teppan, K. Isak, and A. Felfernig . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Affective recommender systems: the role of emotions in recommender systems M. Tkalcic, A. Kosir, and J. Tasic . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 Using latent features diversification to reduce choice difficulty in recommendation list M. Willemsen, B. Knijnenburg, M. Graus, L.Velter Bremmers, and K. Fu . . . . . . . . . . . . . . . . 14 Users’ Decision Behavior in Recommender Interfaces: Impact of Layout Design L. Chen and H. Tsoi . . . . .. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 Visualizable and explicable recommendations obtained from price estimation functions C. Becerra, F. Gonzalez, and A. Gelbukh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 Recommender Systems, Consumer Preferences, and Anchoring Effects G. Adomavicius, J. Bockstedt, S. Curley, and J. Zhang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 Evaluating Group Recommendation Strategies in Memory Based Collaborative Filtering N. Najjar and D. Wilson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 Computing Recommendations for Long Term Data Accessibility basing on Open Knowledge and Linked Data S. Gordea, A. Lindley, and R. Graf . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 UCERSTI 2 Automated Ontology Evolution as a Basis for User Adaptive Recommender Interfaces Elmar P. Wach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .59 A User centric Evaluation of Recommender Algorithms for an Event Recommendation System Simon Dooms, Toon De Pessemier and Luc Martens . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .67 Evaluating Rank Accuracy based on Incomplete Pairwise Preferences Brian Ackerman and Yi Chen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .74 Setting Goals and Choosing Metrics for Recommender System Evaluation Gunnar Schroder, Maik Thiele and Wolfgang Lehner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .78