Popularity Prediction of Videos in YouTube as Case Study: A Regression Analysis Study

Consuming and watching videos in YouTube is an integral part of our daily lives. Predicting videos popularity is of great importance for many services and application ranging from supporting the design and evaluation of a wide range of systems, including the targeted advertising to earn more money, ensure an effective search and recommendation systems, and design an effective caching system. The goal of this paper is to use machine learning techniques to predict the popularity of YouTube videos. Here, we present two simple models from machine learning for predicting the popularity of videos based on videos parameters and the proposed popularity function. The experimental results on YouTube provide a good accuracy of popularity prediction and show the performance of our approach.

[1]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[2]  Ke Xu,et al.  On popularity prediction of videos shared in online social networks , 2013, CIKM.

[3]  Scott Sanner,et al.  Twitter-driven YouTube Views: Beyond Individual Influencers , 2014, ACM Multimedia.

[4]  Xiaolong Jin,et al.  Modeling and Predicting Popularity Dynamics of Microblogs using Self-Excited Hawkes Processes , 2015, WWW.

[5]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[6]  Annika Kangas,et al.  Methods based on k-nearest neighbor regression in the prediction of basal area diameter distribution , 1998 .

[7]  Jussara M. Almeida,et al.  Using early view patterns to predict the popularity of youtube videos , 2013, WSDM.

[8]  Jiangchuan Liu,et al.  Statistics and Social Network of YouTube Videos , 2008, 2008 16th Interntional Workshop on Quality of Service.

[9]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[10]  Alberto Del Bimbo,et al.  Web Video Popularity Prediction using Sentiment and Content Visual Features , 2016, ICMR.

[11]  Hans C. Jessen,et al.  Applied Logistic Regression Analysis , 1996 .

[12]  Huzefa Rangwala,et al.  Digging Digg: Comment Mining, Popularity Prediction, and Social Network Analysis , 2009, 2009 International Conference on Web Information Systems and Mining.

[13]  Tao Mei,et al.  Towards Cross-Domain Learning for Social Video Popularity Prediction , 2013, IEEE Transactions on Multimedia.

[14]  Flavio Figueiredo,et al.  The tube over time: characterizing popularity growth of youtube videos , 2011, WSDM '11.

[15]  J. Townsend.  Theoretical analysis of an alphabetic confusion matrix , 1971 .

[16]  Alan Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[17]  Serge Fdida,et al.  A survey on predicting the popularity of web content , 2014, Journal of Internet Services and Applications.

[18]  M. Hardy.  Regression with dummy variables , 1993 .

[19]  El-Houssine Bouyakhf,et al.  Access and Sharing Contents Through the Social Network: A POMDP Approach , 2017, Comput. Intell..

[20]  Tsuhan Chen,et al.  A latent social approach to YouTube popularity prediction , 2013, 2013 IEEE Global Communications Conference (GLOBECOM).

[21]  Bernardo A. Huberman,et al.  Predicting the popularity of online content , 2008, Commun. ACM.

[22]  H. Bozdogan.  Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions , 1987 .

[23]  Albert-László Barabási,et al.  Modeling and Predicting Popularity Dynamics via Reinforced Poisson Processes , 2014, AAAI.

[24]  W. Mendenhall,et al.  A Second Course in Statistics: Regression Analysis , 1996 .