CAMRa ’10

Challenge on Context-Aware Movie Recommendation

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

  • Shlomo Berkovsky, CSIRO, Australia
  • Ernesto William De Luca, TU Berlin, Germany
  • Alan Said, TU Berlin, Germany
  • Jannis Hermanns, Moviepilot
  • Magnus Hoem, Filmtipset/Entertainity
Workshop Date

September 30, 2010

Web site