In our daily activities we interact with different types of devices, i.e. personal computers, smartphones and tablets, in order to access information. The interactions exploit also different means, such as the usage of mobile applications, the visualization and the upload of user-generated content in social networks, the browsing of a website, and so on. Recommender Systems produce suggestions to users for items, contents, user profiles, etc. they have not considered but might interest them, by analyzing what they previously liked, bought, watched or listened. Such an explicit feedback is an expression of extreme ratings either positive or negative.

In the middle of the range stays a set of different actions in the interface that might be interpreted as feedback, but that needs to be collected implicitly. Even if the literature provides different techniques for collecting implicit feedback, they are tailored for specific types of applications. From the user’s point of view Recommender Systems remain a black box that suggests objects or contents, but the users hardly understand why some items are included in the suggestion list. Providing the users with an understandable representation of how the system represents them would have two types of benefits. On the one hand, the user is able to track the origin of each suggested item, connecting it to a property in the user model. This would increase the user’s trust towards the system. On the other hand, the user may change incorrect attributes and this would lead to more precise recommendations. For instance, it would be possible for the user to search for the latest album of her sister’s favorite band in order to give a present for her birthday. But maybe the user likes a completely different genre. 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 and the goal of this workshop is to solicit the collaboration between recommendation and user interface experts.