Network of Excellence Peer-to-Peer Tagged Media


Following the success of CAMRa2010, we are pleased to announce this year’s Challenge on Context-Aware Movie Recommendation.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. A new movie rating datasete from Moviepilot will be released for the challenge. The dataset contain a number of contextual features, typically not found in standard collaborative filtering datasets. The participating teams are requested to use 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 RecSys2011.


The challenge consists of two tracks: in the first track, the participants are requested to generate recommendations for households, in the second the focus lies on identifying which member of a household performed a specific rating. The dataset is anonymized to protect the users of each service. Participants are expected to use the provided dataset; the use of external information sources, like IMDB, Wikipedia, or NetFlix, is not allowed.
The evaluations should address the following metrics: MAP, P@5, P@10, and AUC. The performance of the teams will be published on an online 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 during the final week of the challenge.


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 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. The papers will be reviewed by the Program Committee based on significance, technical soundness, and presentation clarity. Additionally, the creativity, originality, and scalability will be given special significance during the review process.

Paper submissions and reviews will be handled electronically through the CAMRa page in EasyChair which will be made available in due time for the deadlines.

Data request is now open, send your requests to camra2011 [at]

Contact: Ernesto de Luca, [First name]