ACM Recommender Systems 2010

• Jérôme Picault
• Dimitre Kostadinov
• Pablo Castells
• Alejandro Jaimes

September 30, Workshop Web Site.

This workshop contrives for a new uptake on past experiences and lessons learned from works on recommender systems. We propose an analytic outlook on new research directions, or ones that still require substantial research, with a special focus on their practical adoption in working applications, and the barriers to be met in this path. The workshop will explore gaps between academia and industry considering questions and topics such as the following: What are the main bottlenecks now? What is missing and what are the hot recommender system research topics for the next wave of computing? Is there already a killer application area, and if so, what are the technical and social (privacy, culture) issues we need to consider?

This workshop is an opportunity to bring together researchers and the industry to discuss, on one hand, the main lessons drawn from successes but also from failures of recommender systems, and on the other hand, identify and analyze the major research areas in recommendation and personalization technologies that should be addressed in the future for a practical, effective take-up of the needs of vendors, consumers, and technology providers.
One of the main goals of the workshop is to promote the discussion among the academic researchers and industry practitioners, so the format of the workshop will favour short paper

• Peter Brusilovsky
• Iván Cantador
• Yehuda Koren
• Tsvi Kuflik
• Markus Weimer

September 26, Workshop Web Site

The heterogeneity of information sources can be identified in any of the three pillars of a recommendation algorithm: the modelling of user preferences (e.g., by using explicit and implicit feedback), the description of resource contents (e.g., by making cross domain recommendations), and the exploitation of the context in which recommendations are made (e.g., by jointly considering different contextual aspects). The goal of HetRec workshop is to bring together researchers and practitioners interested in addressing any of the above forms of information heterogeneity in recommender systems, and studying information fusion in this context.

• Nikos Manouselis
• Hendrik Drachsler
• Katrien Verbert
• Olga C. Santos

September 30, Workshop Web Site.

Jointly organised with the 5th European Conference on Technology Enhanced Learning (EC-TEL 2010).

Technology enhanced learning (TEL) aims to design, develop and test socio-technical innovations that will support and enhance learning practices of both individuals and organisations. It is therefore an application domain that generally covers technologies that support all forms of teaching and learning activities. Since information retrieval (in terms of searching for relevant learning resources to support teachers or learners) is a pivotal activity in TEL, the deployment of recommender systems has attracted increased interest. Recommendation methods, techniques and systems open an interesting new approach to facilitate and support learning and teaching. The challenge is to develop, deploy and evaluate systems that provide learners and teachers with meaningful guidance in order to help identify suitable learning resources from a potentially overwhelming variety of choices.

The aim of the RecSysTEL Workshop is to bring together researchers and practitioners that are working on topics related to the design, development and testing of recommender systems in TEL, as well as present the current status of research in this area to interested researchers and practitioners. It will be jointly hosted by the ACM Recommender Systems Conference 2010 (RecSys 2010) and the 5th European Conference on Technology Enhanced Learning (EC-TEL 2010). It aims to create cross-disciplinary liaisons between the RecSys and EC-TEL communities, and serve as a discussion forum where researchers will present the results of their work.

Overall, it aims to outline the rich potential of TEL as an application area for recommender systems, as well as expose participants to the challenges of developing such systems in a TEL context.

• Werner Geyer
• Jill Freyne
• Bamshad Mobasher
• Sarabjot Singh Anand
• Casey Dugan

September 26, Workshop Web Site.

The exponential growth of the social web poses challenges and new opportunities for recommender systems. The social web has turned information consumers into active contributors creating massive amounts of information. Finding relevant and interesting content at the right time and in the right context is challenging for existing recommender approaches. At the same time, social systems by their definition encourage interaction between users and both online content and other users, thus generating new sources of knowledge for recommender systems. Web 2.0 users explicitly provide personal information and implicitly express preferences through their interactions with others and the system (e.g. commenting, friending, rating, etc.). These various new sources of knowledge can be leveraged to improve recommendation techniques and develop new strategies which focus on social recommendation. The Social Web provides huge opportunities for recommender technology and in turn recommender technologies can play a part in fuelling the success of the Social Web phenomenon. The goal of this workshop is to bring together researcher and practitioners to explore, discuss, and understand challenges and new opportunities for recommender systems and the Social Web.

• Amélie Anglade
• Claudio Baccigalupo
• Norman Casagrande
• Òscar Celma
• Paul Lamere

September 26, Workshop Web Site.

In the last decade, digital music has transformed the landscape of music experience and distribution. Personal music collections can exceed thousands of tracks, while the Internet has made it simpler than ever to find and access music. In this scenario, music recommendation systems have become increasingly important for listeners to discover and navigate music.

Music-centric recommenders such as Last.fm and Pandora have enjoyed commercial and critical success. But how well do these systems work? How good are the recommendations? How far into the “long tail” can they go before surrendering to bad quality works?

The approach of recommending songs as if they were books is limiting; better results can be achieved by taking into account the peculiarities of music and the music recommendation process. A successful music recommender should combine insights from user preferences (classical collaborative filtering) with the content (audio analysis, tags, lyrics, etc..) while integrating the social interactions along with the psychological and emotional aspects connected to music consumption.

The Workshop on Music Recommendation and Discovery is meant to be a platform where the Recommender System, Music Information Retrieval, User Modeling, Music Cognition, and Music Psychology communities can meet, exchange ideas and collaborate.

• Bart P. Knijnenburg
• Lars Schmidt-Thieme
• Dirk G. F. M. Bollen

September 30, Workshop Web Site.

At the RecSys 2009 conference, Francisco Martin indicated that the main challenge for recommender systems is to provide users with a usable and intuitive interface. Theorizing about consumer decision processes and measuring user satisfaction in online tests is however no common practice in the recommender systems field.

Meanwhile, 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. Likewise, the field of Human-Computer Interaction has been studying the usability of interfaces for ages, but does not seem to connect the dots between research on consumer choice, and recommender system interfaces.

The UCERSTI workshop tries to bridge the gaps between these fields by providing a platform for Human-Recommender Interaction research.

• Gediminas Adomavicius
• Alexander Tuzhilin
• Shlomo Berkovsky
• Ernesto William De Luca
• Alan Said

September 26 and September 30,
CARS: Workshop Web Site.
CAMRa: Workshop Web Site.

The importance of contextual information has been recognized by researchers and practitioners in many disciplines, including e-commerce, personalization, information retrieval, ubiquitous and mobile computing, data mining, marketing, and management. While a substantial research has already been performed in the area of recommender systems, the vast majority of existing approaches focuses on recommending the most relevant items to users and does not take into account additional contextual information, such as time, location, weather, or the company of other people. Therefore, this joint workshop and challenge aim to bring together researchers with wide-ranging backgrounds to identify important research questions, to exchange ideas from different research disciplines, and, more generally, to facilitate discussion and innovation in the area of context-aware recommender systems (CARS) and tackle practical challenges of context-aware movie recommendation (CAMRa).

CARS-2010 builds on the success of the first Workshop on Context-Aware Recommender Systems (CARS-2009) and will focus on the general issues encountered in context-aware recommendations, including novel research approaches, promising research directions, and important practical applications.

CAMRa is set up as a challenge, where representatives from research and industry working on context-aware movie recommenders, will be able to exchange ideas and results. Two datasets, one from Moviepilot and one from Filmtipset, will be released. The datasets contain a number of contextual features, typically not found in standard collaborative filtering datasets, i.e., social network, intended audience, mood, etc. The challenge focuses on classification and ranking accuracy metrics of context-aware recommendation algorithms for movies. The participating teams will use one or more of the additional contextual features to generate context-aware recommendations. CAMRa submissions are expected to focus on the challenge and algorithms evaluated using the released datasets and will be reviewed by a panel of distinguished researchers.