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 knowledge on what the users are experiencing.
Therefore, the user interface engineering community can play a crucial role in the design of more effective 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. It is also widely-known that a current challenge in the recommender systems research is to go beyond accuracy, since the acceptance of a recommendation by the user is related to a set of other factors, such as the way in which the recommended items are presented to the user. Therefore, an analysis of the capability of the user interface to improve both the effectiveness and the understanding of the recommendations is an aspect of central interest in this research area.
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 offering 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 Being able to control the user model, in order to discard outdated preferences or preferences that are related to other users (e.g., when a profile is used to buy a gift for another person) is another crucial aspect.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. Therefore, the goal of this workshop is to solicit the collaboration between recommendation and user interface experts.
This workshop solicits contributions in all topics related to engineering Computer-Human Interaction in Recommender Systems, focused (but not limited) to the following list:
- 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 effectiveness for recommendation and personalization purposes.
We will consider three different submission types, all in the ACM SIGCHI format: regular (6 pages), short (4 pages) and extended abstracts (2 pages). A link to a short video (e.g. 5 minutes) may be also submitted.
Research and position papers (regular or short) should be clearly placed with respect to the state of the art and state the contribution of the proposal in the domain of application, even if presenting preliminary results. In particular, research papers should describe the methodology in detail, experiments should be repeatable, and a comparison with the existing approaches in the literature should be made where possible. Position papers should introduce novel point of views in the workshop topics or summarize the experience of a researcher or a group in the field.
Practice and experience reports (short) should present in detail the real-world scenarios in which Computer-Human Interaction is engineered for recommendation purposes.
Demo proposals (extended abstract) should present the details of a prototype or complete application that engineers Computer-Human Interaction in Recommender Systems. The systems will be demonstrated to the workshop attendees.
The reviewing process will be coordinated by the organizers. Each paper will receive three reviews: two externals to the organizing committee and one internal. The external reviewers will be contacted according to their expertise in the paper topic.
All accepted papers will be made available on the workshop website together with the material generated during the meeting. Moreover, the proceedings of the workshop will be published in a volume that will be indexed by the main databases, such as DBLP and Scopus (more details on this volume will be given soon). Authors of selected papers will be invited to submit an extended version in a journal special issue.
Workshop participants are encouraged to present a poster about their contributions or workshop results at the main conference, EICS 2017.
All submissions have to be prepared according to the CHI Archive Format and submitted in PDF format through the workshop management system at EasyChair.
- Paper Submission: April 9, 2017
- Author Notification: April 26, 2017
- Early registration deadline: May 1, 2017
- Workshop at EICS: June 26, 2017