Social Connections in User-Generated Content Video Systems: Analysis and Recommendation

Zhenyu Li (1) , Jiali Lin (1, 2) , Gaogang Xie (1)

1 ICT - Institute of Computing Technology [Beijing]
2 Computer and Communication School

User Generated Content video systems are by definition heavily depending on the input of their community of users and their social interactions for video diffusion and opinion sharing. Nevertheless, we show in this paper, through a measurement and analysis of YouKu, the most popular UGC video system in China, that the social connectivity of its users is very low.These results are consistent with what reported about YouTube in previous works. As a UGC system can benefit from audience increase through improved connectivity, our findings motivate us to propose a mean to enhance the connectivity by taking benefit of friend recommendation. To this end, we assess two similarity metrics, where users' interests are derived from their uploads and favorites tagging of videos, to evaluate the interest similarity between friends. The results consistently show that friends share to a great extent common interests. Two friend recommendation algorithms are then proposed that propose potential friends with similar interests as measured by the similarity metrics that can be derived by publicly information provided by users. Experiments on the dataset of Youku desmonstrate that the social connectivity can be greatly enhanced by our friend proposition and that users can access to a larger set of interesting videos through their recommendations.

Mots clés: UGC systems; social connection; user interest; friend recommendation; tag augmentation

Domaines: Réseaux et télécommunications [cs.NI]

Zhenyu Li, Jiali Lin, Gaogang Xie. Social Connections in User-Generated Content Video Systems: Analysis and Recommendation. IEEE Transactions on Network and Service Management, 2013, 10 (1), pp.70-84. ⟨10.1109/TNSM.2012.100512.120233⟩. ⟨hal-00876525⟩