Abstract: Methods, system and computer readable medium for discovering social groups include extracting activity related data associated with a user's social interactions from a source. The activity related data identifies information related to social contacts used during the social interactions at the source. The activity related data of the user is analyzed to identify co-occurrences of the social contacts. The co-occurrences determine a set of related contacts. The set of related contacts identified from the activity related data are clustered into distinct social groups. The social groups are used by a user to facilitate subsequent interactions.

Abstract: Methods, system and computer readable medium for discovering social groups include extracting activity related data associated with a user's social interactions from a source. The activity related data identifies information related to social contacts used during the social interactions at the source. The activity related data of the user is analyzed to identify co-occurrences of the social contacts. The co-occurrences determine a set of related contacts. The set of related contacts identified from the activity related data are clustered into distinct social groups. The social groups are used by a user to facilitate subsequent interactions.

Abstract: Collaborative-filtering software creates a neighborhood using a map-reduce architecture by pair-wise application of a similarity measure to a sparse matrix of users and items of media designated by the users. The collaborative-filtering software then generates recommendations for a particular user by rating items of media designated by other users in the neighborhood (but not the particular user). The collaborative-filtering software rates the item of media, using a weighted vote of the users in the neighborhood. The weighted vote depends at least in part on the mean similarity of the users in the neighborhood who have designated the item of media. Then the collaborative-filtering software records the item of media as a recommendation for subsequent presentation to the other user, if the rating of the item of media is among the highest in comparison to the ratings of other items of media designated by users in the neighborhood.

Abstract: Collaborative-filtering software creates a neighborhood using a map-reduce architecture by pair-wise application of a similarity measure to a sparse matrix of users and items of media designated by the users. The collaborative-filtering software then generates recommendations for a particular user by rating items of media designated by other users in the neighborhood (but not the particular user). The collaborative-filtering software rates the item of media, using a weighted vote of the users in the neighborhood. The weighted vote depends at least in part on the mean similarity of the users in the neighborhood who have designated the item of media. Then the collaborative-filtering software records the item of media as a recommendation for subsequent presentation to the other user, if the rating of the item of media is among the highest in comparison to the ratings of other items of media designated by users in the neighborhood.