EXPLOITING SOCIAL CONTEXTS FOR MOVIE RECOMMENDATION

Abstract

A social networking service (SNS) allows users to share information with family, friends, and communities. Since there are many kinds of information uploaded and shared through an SNS, the amount of information on such siteskeeps increasing exponentially. In particular, Facebook has adopted some interesting features related to entertainment (e. g., movies, music, and TV shows). However, they do not consider contextual information of users for recommendations (e. g., time, location, and social context). Therefore, in this paper, we propose a novel approach for movie recommendations based on the integration ofa variety ofcontextual information (i.e., when the users watched the movies, where the users watched the movies, and who watched the movie with them). Thus, we developed a Facebook application (called MyMovieHistory) for recording the movie history of users and recommending relevant movies.