- Apologies for cross-posting
- Please forward to your students/colleagues, who might consider participating
CALL FOR PAPERS AND PARTICIPATION
CAMRa-2010 :: Challenge on Context-aware Movie Recommendation, part of the joint event on
Context-Aware Recommender Systems Research Workshop and Movie Recommendation Challenge at the 2010 ACM Recommender Systems Conference, Barcelona, September 26-30, 2010
Challenge (CAMRa, Sep 30): http://www.dai-labor.de/camra2010/
Workshop (CARS, Sep 26): http://ids.csom.umn.edu/faculty/gedas/cars2010/
The majority of existing recommendation approaches does not take into account contextual information, such as time, location, or weather. This challenge aims to tackle the practical issue of context-aware movie recommendation. Two new movie ratings datasets, one from Moviepilot and one from Filmtipset, are released for the challenge. The datasets contain a number of contextual features, typically not found in standard collaborative filtering datasets. The participating teams are requested to the additional contextual features to generate context-aware recommendations.
The challenge focuses on classification accuracy metrics. The participants are invited to submit papers focusing on the challenge to the workshop, which will be conducted in conjunction with RecSys-2010. The winners of the challenge will be invited to submit extended versions of their papers to the follow-up special issue on context-aware recommendations (not confirmed yet).
The challenge consists of three tracks: one track is common for both datasets and a separate for each dataset. Participating teams are invited to take part in any track. The number of tracks a team is participating in is not limited. Both datasets are anonymized to protect the users of each service. Participants are expected to use the provided datasets; the use of external information sources, like IMDB, Wikipedia, or NetFlix, is not allowed.
The challenge tracks are:
* Weekly Recommendation. Focuses on the temporal dimension of context. The participants are asked to recommend movies for two different weeks: the Christmas week and the week leading to the Oscars ceremony. For this track, any of the two datasets can be used. The algorithms used for each dataset may differ.
* Moviepilot Track. Focuses on the mood of movies. The participants are asked to recommend a list of movies for a selection of users based on a given mood.
* Filmtipset Track. Focuses on the social connections between users. The participants are asked to recommend a list of movies for a selection of users based on the friend relations in the social network.
The evaluations should address the following metrics: MAP, P@5, P@10, and AUC. The performance of the teams will be published on the leaderboard. Additional datasets will be released for the final evaluation to identify the winners of each track. An online evaluation with real users will be conducted in some tracks.
There are four datasets available: Moviepilot_week, Filmtipset_week, Moviepilot_mood, Filmtipset_social. To access the datasets, please send an inquiry stating which dataset(s) you request, your affiliation, and which track(s) you intend to participate in to [log in to unmask] The request will help the organizers to estimate the number of participants.
Call for Papers:
The participants are invited to submit papers focusing on the challenge and algorithms evaluated using the released datasets. The submissions are limited to 8 pages in the ACM SIG proceedings format. Each submission should be accompanied by a 1-page summary of the algorithm. The papers will be reviewed by the Program Committee based on significance, technical soundness, and presentation clarity. The 1-page summaries will be reviewed by the Expert Panel based on creativity, originality, and scalability.
Paper submissions and reviews will be handled electronically through the CAMRa page in EasyChair (will be available later). The authors of high-quality papers will be invited to submit the extended versions of their work to a planned journal on context-awareness in recommender systems.
* Paper submission: July 1, 2010
* Notification: July 22, 2010
* Camera-ready submission: August 16, 2010
* 1-pager summary submission: August 16, 2010
* Feedback from the Expert Panel: September 10, 2010
* Winners announced: RecSys dinner
* Workshop: September 30, 2010
Organizers and Committees:
General Chairs ([log in to unmask])
* Shlomo Berkovsky, CSIRO
* Ernesto William De Luca, DAI Lab/Technische Universität Berlin
* Alan Said, DAI Lab/Technische Universität Berlin
* Jannis Hermanns, Moviepilot
* Magnus Hoem, Filmtipset/Entertainity
* Sahin Albayrak, DAI-Laboratory/Technische Universität Berlin, Germany
* Liliana Ardissono, Università degli Studi di Torino, Italy
* Lora Aroyo, Free University Amsterdam, The Netherlands
* Stephan Baumann, DFKI, Germany
* Dominik Benz, University of Kassel, Germany
* Toine Bogers, Royal School of Library Information Science, Denmark
* Li Chen, Hong Kong Baptist University, China
* Jill Freyne, CSIRO, Australia
* Ido Guy, IBM Research, Israel
* Tom Heath, Talis, UK
* Robert Jäschke, University of Kassel, Germany
* Jérôme Kunegis, DAI-Laboratory/Technische Universität Berlin, Germany
* Leandro Balby Marinho, Universität Hildesheim, Germany
* Jon Sanders, Netflix, USA
* Rene Schult, Otto-von-Guericke-Magdeburg, Germany
* Bracha Shapira, Ben Gurion University, Israel
* Myra Spiliopoulou, Otto-von-Guericke-Magdeburg, Germany
* Domonkos Tikk, Budapest University of Technology and Economics, Hungary
* Robert Wetzker, Technische Universität Berlin, Germany
* Gedas Adomavicius, University of Minnesota, USA
* Sarabjot Singh Anand, University of Warwick, UK
* Derek Bridge, University College Cork, Ireland
* Anthony Jameson, DFKI, Germany
* Joseph Konstan, University of Minnesota, USA
* Yehuda Koren, Yahoo! Research, Israel
* Francisco Martin, Strands, Spain
* Bamshad Mobasher, DePaul University, USA
* Francesco Ricci, Free University of Bozen-Bolzano, Italy
* Barry Smyth, University College Dublin, Ireland
* Alex Tuzhilin, New York University, USA
* Qiang Yang, Hong Kong University of Science and Technology, China
The CARS workshop builds upon the success of the 1st Workshop on Context-Aware Recommender Systems (CARS-2009) held in New York in October 2009, which brought together an international group of researchers to explore the importance and use of contextual information in recommender systems as well as to discuss new research directions.
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 amount of 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 any additional contextual information, such as time, location, weather, or the company of other people. Therefore, this workshop aims 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). In particular, topics of interest for this workshop include (but are not limited to):
-- Context modeling techniques for recommender systems;
-- Context-aware user modeling for recommender systems;
-- Data sets for context-dependent recommendations;
-- Algorithms for detecting the relevance of contextual data;
-- Algorithms for incorporating contextual information into recommendation process;
-- Algorithms for building explicit dependencies between contextual features and ratings;
-- Interacting with context-aware recommender systems;
-- Novel applications for context-aware recommender systems;
-- Large-scale context-aware recommender systems;
-- Evaluation of context-aware recommender systems.
Additional information on CARS available at: http://ids.csom.umn.edu/faculty/gedas/cars2010/
M.Sc.(Eng.) Alan Said
Compentence Center Information Retrieval & Machine Learning Technische Universität Berlin DAI-Laboratory Sekr. TEL 14 Ernst-Reuter-Platz 7
10587 Berlin / Germany
Phone: 0049 - 30 - 314 74072
Fax: 0049 - 30 - 314 74003
E-mail: [log in to unmask]