A statistical and clustering study on Youtube 2D and 3D video recommendation graph

Social network sites, like Facebook, Tweeter and Flickr provide users the opportunity to share their media content, such as videos, music tracks or photos. Beyond the fact that they can share information the users can also vote or comment on information posted by other users. Social networks take advantage of this activity and create groups and communities of users with similar interests. This categorization helps social network systems to support users with data, e.g. videos, photos or users profiles, that are relevant to their interests. In order to increase the effectiveness of navigation, analysis of social media content graphs needs to be done. In this paper, an analysis of the Youtube social media graph is presented. Graphs of 2D and 3D videos are considered in this analysis. Well known properties of web and social networks analysis, like the power-law distribution are discussed. Moreover, clustering methods are applied in order to study the existence of media content groups. Finally, the results of our analysis are discussed and directions of future work are presented.