Forecasting Popularity of Videos Using Social Media

Jie Xu, Mihaela Van Der Schaar, Jiangchuan Liu, Haitao Li

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media. Social-Forecast explicitly considers the dynamically changing and evolving propagation patterns of videos in social media when making popularity forecasts, thereby being situation and context aware. Social-Forecast aims to maximize the forecast reward, which is defined as a tradeoff between the popularity prediction accuracy and the timeliness with which a prediction is issued. The forecasting is performed online and requires no training phase or a priori knowledge. We analytically bound the prediction performance loss of Social-Forecast as compared to that obtained by an omniscient oracle and prove that the bound is sublinear in the number of video arrivals, thereby guaranteeing its short-term performance as well as its asymptotic convergence to the optimal performance. In addition, we conduct extensive experiments using real-world data traces collected from the videos shared in RenRen, one of the largest online social networks in China. These experiments show that our proposed method outperforms existing view-based approaches for popularity prediction (which are not context-aware) by more than 30% in terms of prediction rewards.

Original languageEnglish (US)
Article number6955832
Pages (from-to)330-343
Number of pages14
JournalIEEE Journal on Selected Topics in Signal Processing
Volume9
Issue number2
DOIs
StatePublished - Mar 1 2015
Externally publishedYes

Fingerprint

Experiments

Keywords

  • Forecasting algorithm
  • online learning
  • online social networks
  • popularity prediction
  • situational and contextual awareness
  • social media

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing

Cite this

Forecasting Popularity of Videos Using Social Media. / Xu, Jie; Van Der Schaar, Mihaela; Liu, Jiangchuan; Li, Haitao.

In: IEEE Journal on Selected Topics in Signal Processing, Vol. 9, No. 2, 6955832, 01.03.2015, p. 330-343.

Research output: Contribution to journalArticle

Xu, Jie ; Van Der Schaar, Mihaela ; Liu, Jiangchuan ; Li, Haitao. / Forecasting Popularity of Videos Using Social Media. In: IEEE Journal on Selected Topics in Signal Processing. 2015 ; Vol. 9, No. 2. pp. 330-343.
@article{61c847b993364459a82ea9bed423f687,
title = "Forecasting Popularity of Videos Using Social Media",
abstract = "This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media. Social-Forecast explicitly considers the dynamically changing and evolving propagation patterns of videos in social media when making popularity forecasts, thereby being situation and context aware. Social-Forecast aims to maximize the forecast reward, which is defined as a tradeoff between the popularity prediction accuracy and the timeliness with which a prediction is issued. The forecasting is performed online and requires no training phase or a priori knowledge. We analytically bound the prediction performance loss of Social-Forecast as compared to that obtained by an omniscient oracle and prove that the bound is sublinear in the number of video arrivals, thereby guaranteeing its short-term performance as well as its asymptotic convergence to the optimal performance. In addition, we conduct extensive experiments using real-world data traces collected from the videos shared in RenRen, one of the largest online social networks in China. These experiments show that our proposed method outperforms existing view-based approaches for popularity prediction (which are not context-aware) by more than 30{\%} in terms of prediction rewards.",
keywords = "Forecasting algorithm, online learning, online social networks, popularity prediction, situational and contextual awareness, social media",
author = "Jie Xu and {Van Der Schaar}, Mihaela and Jiangchuan Liu and Haitao Li",
year = "2015",
month = "3",
day = "1",
doi = "10.1109/JSTSP.2014.2370942",
language = "English (US)",
volume = "9",
pages = "330--343",
journal = "IEEE Journal on Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Forecasting Popularity of Videos Using Social Media

AU - Xu, Jie

AU - Van Der Schaar, Mihaela

AU - Liu, Jiangchuan

AU - Li, Haitao

PY - 2015/3/1

Y1 - 2015/3/1

N2 - This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media. Social-Forecast explicitly considers the dynamically changing and evolving propagation patterns of videos in social media when making popularity forecasts, thereby being situation and context aware. Social-Forecast aims to maximize the forecast reward, which is defined as a tradeoff between the popularity prediction accuracy and the timeliness with which a prediction is issued. The forecasting is performed online and requires no training phase or a priori knowledge. We analytically bound the prediction performance loss of Social-Forecast as compared to that obtained by an omniscient oracle and prove that the bound is sublinear in the number of video arrivals, thereby guaranteeing its short-term performance as well as its asymptotic convergence to the optimal performance. In addition, we conduct extensive experiments using real-world data traces collected from the videos shared in RenRen, one of the largest online social networks in China. These experiments show that our proposed method outperforms existing view-based approaches for popularity prediction (which are not context-aware) by more than 30% in terms of prediction rewards.

AB - This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media. Social-Forecast explicitly considers the dynamically changing and evolving propagation patterns of videos in social media when making popularity forecasts, thereby being situation and context aware. Social-Forecast aims to maximize the forecast reward, which is defined as a tradeoff between the popularity prediction accuracy and the timeliness with which a prediction is issued. The forecasting is performed online and requires no training phase or a priori knowledge. We analytically bound the prediction performance loss of Social-Forecast as compared to that obtained by an omniscient oracle and prove that the bound is sublinear in the number of video arrivals, thereby guaranteeing its short-term performance as well as its asymptotic convergence to the optimal performance. In addition, we conduct extensive experiments using real-world data traces collected from the videos shared in RenRen, one of the largest online social networks in China. These experiments show that our proposed method outperforms existing view-based approaches for popularity prediction (which are not context-aware) by more than 30% in terms of prediction rewards.

KW - Forecasting algorithm

KW - online learning

KW - online social networks

KW - popularity prediction

KW - situational and contextual awareness

KW - social media

UR - http://www.scopus.com/inward/record.url?scp=84961596410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961596410&partnerID=8YFLogxK

U2 - 10.1109/JSTSP.2014.2370942

DO - 10.1109/JSTSP.2014.2370942

M3 - Article

AN - SCOPUS:84961596410

VL - 9

SP - 330

EP - 343

JO - IEEE Journal on Selected Topics in Signal Processing

JF - IEEE Journal on Selected Topics in Signal Processing

SN - 1932-4553

IS - 2

M1 - 6955832

ER -