Predicting YouTube content popularity via Facebook data

A network spread model for optimizing multimedia delivery

Dinuka A. Soysa, Denis Guangyin Chen, Oscar C. Au, Amine Bermak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages214-221
Number of pages8
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: 16 Apr 201319 Apr 2013

Other

Other2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period16/4/1319/4/13

Fingerprint

Websites
Servers
Statistics
Internet
Bandwidth

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Soysa, D. A., Chen, D. G., Au, O. C., & Bermak, A. (2013). Predicting YouTube content popularity via Facebook data: A network spread model for optimizing multimedia delivery. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 214-221). [6597239] https://doi.org/10.1109/CIDM.2013.6597239

Predicting YouTube content popularity via Facebook data : A network spread model for optimizing multimedia delivery. / Soysa, Dinuka A.; Chen, Denis Guangyin; Au, Oscar C.; Bermak, Amine.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 214-221 6597239.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Soysa, DA, Chen, DG, Au, OC & Bermak, A 2013, Predicting YouTube content popularity via Facebook data: A network spread model for optimizing multimedia delivery. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6597239, pp. 214-221, 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 16/4/13. https://doi.org/10.1109/CIDM.2013.6597239
Soysa DA, Chen DG, Au OC, Bermak A. Predicting YouTube content popularity via Facebook data: A network spread model for optimizing multimedia delivery. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 214-221. 6597239 https://doi.org/10.1109/CIDM.2013.6597239
Soysa, Dinuka A. ; Chen, Denis Guangyin ; Au, Oscar C. ; Bermak, Amine. / Predicting YouTube content popularity via Facebook data : A network spread model for optimizing multimedia delivery. Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 214-221
@inproceedings{b53890d5c7c4465990feebf02ec13b3e,
title = "Predicting YouTube content popularity via Facebook data: A network spread model for optimizing multimedia delivery",
abstract = "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.",
author = "Soysa, {Dinuka A.} and Chen, {Denis Guangyin} and Au, {Oscar C.} and Amine Bermak",
year = "2013",
doi = "10.1109/CIDM.2013.6597239",
language = "English",
isbn = "9781467358958",
pages = "214--221",
booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

TY - GEN

T1 - Predicting YouTube content popularity via Facebook data

T2 - A network spread model for optimizing multimedia delivery

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

UR - http://www.scopus.com/inward/citedby.url?scp=84885576590&partnerID=8YFLogxK

U2 - 10.1109/CIDM.2013.6597239

DO - 10.1109/CIDM.2013.6597239

M3 - Conference contribution

SN - 9781467358958

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

ER -