Recommender Systems (RSs) have proved to be a valuable kind of adaptive and intelligent systems for coping with the information overload problem. In recent years, the interest in RSs has dramatically increased: While a lot of discussion has been made on recommendation techniques and algorithms, few studies have stood from users' angles to consider their acceptance of recommendations. Characterizing and evaluating the quality of user experience and users' subjective attitudes toward the acceptance of recommender technology is an important issue which merits attention from researchers and practitioners in both web technology and human factor fields. Therefore, the main goal of the workshop is to stimulate the discussion around problems, challenges and research directions about the acceptance of recommender technology.
Preface
Some questions motivate this workshop: 1. What does influence and determine the acceptance of the suggestions computed by a RS? 2. How does the presentation of the computed recommendations can increase the acceptance of the suggestions and of the whole system? 3. How explanation techniques can contribute to establish trust? 4. Are there general rules or guidelines for system design that can be proved to be effective in influencing the user acceptance? 5. How the recommendations should be adapted to the context of the human computer interaction to increase their acceptance? 6. What Persuasion strategies could be more effective in increasing the recommendation take up? 7. What kinds of decision processes occur in users of recommender systems, and how RSs can support these processes? In particular, the workshop will focus on the following aspects:
Presentation: How the system presents and visualizes the computed recommendations is obviously a critical factor for the acceptance and helpfulness of the recommendations and the RS.
Explanation: Presentation and explanation techniques are not easily separable. A good presentation technique is also capable of explaining recommendations but also in motivating the user to make further requests, including requests for explanations.
Trust: Previous research indicates that transparency and the possibility of interaction with RSs increase user trust, defined as perceived confidence in a RS competence. Users may be more forgiving, and more confident in recommendations, if they understand why a bad recommendation has been made. In addition, the interface design of a RS may affect its credibility, in particular the importance of explanation interfaces in increasing user acceptance has been well recognized in a number of fields.
Persuasion: Systems based on persuasion techniques can actively modify the user preferences and perceptions on the proposed items. Recommender systems may combine presentation and persuasion techniques to raise the expected utility of the suggested items. Decision support: A complementary perspective on recommender systems sees them as decision support systems that help users to make better choices. From this perspective, the focus is more on the various types of information that users require to make satisfactory decisions, including, for example, information that will enable them to justify their decisions to other people.
We would like to thank all the authors for their submissions, and our Program Committee for their precious work.
June 2011 Francesco Ricci Giovanni Semeraro Marco de Gemmis Pasquale Lops Program Committee