TY - GEN
T1 - Predicting YouTube content popularity via Facebook data
T2 - 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
AU - Soysa, Dinuka A.
AU - Chen, Denis Guangyin
AU - Au, Oscar C.
AU - Bermak, Amine
PY - 2013
Y1 - 2013
N2 - The recent popularity of social networking websites have resulted in a greater usage of internet bandwidth for sharing multimedia content through websites such as Facebook and YouTube. Moving large volumes of multi-media data through limited network resources remains a technical challenge to this day. The current state-of-art solution in optimizing cache server utilization depends heavily on efficient caching policies to determine content priority. This paper proposes a Fast Threshold Spread Model (FTSM) to predict the future access pattern of multi-media content based on the social information of its past viewers. The prediction results are compared and evaluated against ground truth statistics of the respective YouTube video. A complexity analysis on the proposed algorithm for large datasets along with the correlation between Facebook social sharing and YouTube global hit count are explored.
AB - The recent popularity of social networking websites have resulted in a greater usage of internet bandwidth for sharing multimedia content through websites such as Facebook and YouTube. Moving large volumes of multi-media data through limited network resources remains a technical challenge to this day. The current state-of-art solution in optimizing cache server utilization depends heavily on efficient caching policies to determine content priority. This paper proposes a Fast Threshold Spread Model (FTSM) to predict the future access pattern of multi-media content based on the social information of its past viewers. The prediction results are compared and evaluated against ground truth statistics of the respective YouTube video. A complexity analysis on the proposed algorithm for large datasets along with the correlation between Facebook social sharing and YouTube global hit count are explored.
UR - http://www.scopus.com/inward/record.url?scp=84885576590&partnerID=8YFLogxK
U2 - 10.1109/CIDM.2013.6597239
DO - 10.1109/CIDM.2013.6597239
M3 - Conference contribution
AN - SCOPUS:84885576590
SN - 9781467358958
T3 - Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
SP - 214
EP - 221
BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Y2 - 16 April 2013 through 19 April 2013
ER -