Since the emergence of recommender systems, a large majority of research focuses on objective accuracy criteria and less attention has been paid to how users interact with the system and the efficacy of interface designs from users' perspective. Well-designed user interfaces have the capability of enhancing user interaction experience and overall satisfaction. For example, explanation interfaces can increase user confidence in their decision choices and inspire user trust and loyalty to the used system. Nowadays, a variety of novel recommendation technologies have been developed to meet different needs (e.g., group and social recommenders). Recommender systems have also extended to new application platforms (e.g., mobile devices). In addition, heterogeneous information resources have been incorporated into recommender systems (e.g., psychological factors, social media). This brings forward new challenges in designing effective and efficient interfaces for these new recommender applications.
This half-day workshop brought together researchers and practitioners around the topics of designing and evaluating novel intelligent interfaces for recommender systems in order to: (1) share research and techniques, including new design technologies and evaluation methodologies (2) identify next key challenges in the area, and (3) identify emerging topics. This workshop aimed to create an interdisciplinary community with a focus on the interface design issues for recommender systems and promoting the collaboration opportunities between researchers and practitioners.
The papers in this volume discuss the following three key issues:
• Visualization and exploration in large and multi-dimensional datasets
• Social aspects of interfaces
The paper "TopicLens: An Interactive Recommender System based on Topical and Social Connections" looks at visualization of data sets. The authors use a river interface metaphor for navigating topics, items as well as people in three case studies: Twitter, New York Times articles and movies via the Facebook API. The paper "CoFeel: Using Emotions for social interaction in Group Recommender Systems" surveys the social interaction between users, and considers how they interact with each other using emotions in a mobile based feedback interface. The paper "Graph Embeddings for Movie Visualization and Recommendation" proposes a novel way of navigating and exploring a large number of recommendations visually, using a dendogram representation. A demo of this interface is available at: http://graph.bunchwars.com/.
We would like to thank all the authors for their submissions, our Program Committee and subreviewers for their precious work.
August 2012