A user usually gets the same suggesting results as everyone else in most of the multimedia social services, nowadays. To address the challenging problem of personalization in the social network, we propose a method which exploits user''s activities, user''s moods, and user''s friend relationships from the social network to build a decision-making system. Depending on a current state of the user''s mood, this system infers the most appropriated video for the user. In the system, the user evaluates a set of the given recommendation methods which extract from the user''s database social network and assigns a vague value to each method by a weight. Then, we find the fuzzy collection solution for the system and classify the set of methods into subsets, and order the subsets based on its local dominance to choose the best appropriate method. Finally, we conduct an experiment using the YouTube API with a lot of video types. The experiment result shows that the channel recommendation system appropriately affords the user''s character, it is more satisfying than the current YouTube based on an evaluation of several users.