Explaining collaborative filtering recommendations
CSCW '00 Proceedings of the 2000 ACM conference on Computer supported cooperative work
Evaluating collaborative filtering recommender systems
ACM Transactions on Information Systems (TOIS)
Accurately interpreting clickthrough data as implicit feedback
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
The dynamics of viral marketing
EC '06 Proceedings of the 7th ACM conference on Electronic commerce
Event detection from evolution of click-through data
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Hi-index | 0.00 |
Social media systems such as YouTube are gaining phenomenal popularity. As they face increasing pressure and difficulties monetising the large amount of user-generated content, there are intense interests in technologies capable of delivering revenue to the owners. In this paper, we propose to use data mining techniques to help companies increase their revenue stream. Our approach differs principally in the underlying monetisation model and hence, the algorithms and data utilised. Our new model assumes both consumer and commercial content being entirely user-generated. We first present an algorithm to demonstrate one of possible monetisation technique that could be used in social media systems such as YouTube. A large volume of real-data harvested from YouTube will also be discussed and made available for the community to potentially kick start research in this direction.