• DocumentCode
    1663435
  • Title

    The MovieOracle - Content Based Movie Recommendations

  • Author

    Nessel, Jochen ; Cimpa, Barbara

  • Author_Institution
    EdgeWorks Software Ltd. Ho Chi Minh City, Ho Chi Minh City, Vietnam
  • Volume
    3
  • fYear
    2011
  • Firstpage
    361
  • Lastpage
    364
  • Abstract
    "What movies do you like?" Everyone has had to answer this question at least once. And the answer is often given by means of examples: "I like Star Wars." Often an examples explains a lot more than trying to characterize movies by other means, like giving a category like "Science Fiction" or providing actor or director names. The Movie Oracle recommends movies by comparing examples provided by the user to movie contents, which the Movie-Oracle derives from the movie dialogues gathered from movie subtitle files, without using any human generated meta-data.
  • Keywords
    meta data; question answering (information retrieval); recommender systems; MovieOracle; Science Fiction; content based movie recommendation; human generated metadata; movie content; question answering; Books; Humans; Internet; Motion pictures; Prediction algorithms; Prototypes; Servers; content based prediction; inductive learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Web Intelligence and Intelligent Agent Technology (WI-IAT), 2011 IEEE/WIC/ACM International Conference on
  • Conference_Location
    Lyon
  • Print_ISBN
    978-1-4577-1373-6
  • Electronic_ISBN
    978-0-7695-4513-4
  • Type

    conf

  • DOI
    10.1109/WI-IAT.2011.236
  • Filename
    6040879