Advanced search
2 files | 2.35 MB Add to list

Modeling and predicting the popularity of online news based on temporal and content-related features

Steven Van Canneyt (UGent) , Philip Leroux (UGent) , Bart Dhoedt (UGent) and Thomas Demeester (UGent)
(2018) MULTIMEDIA TOOLS AND APPLICATIONS. 77(1). p.1409-1436
Author
Organization
Abstract
As the market of globally available online news is large and still growing, there is a strong competition between online publishers in order to reach the largest possible audience. Therefore an intelligent online publishing strategy is of the highest importance to publishers. A prerequisite for being able to optimize any online strategy, is to have trustworthy predictions of how popular new online content may become. This paper presents a novel methodology to model and predict the popularity of online news. We first introduce a new strategy and mathematical model to capture view patterns of online news. After a thorough analysis of such view patterns, we show that well-chosen base functions lead to suitable models, and show how the influence of day versus night on the total view patterns can be taken into account to further increase the accuracy, without leading to more complex models. Second, we turn to the prediction of future popularity, given recently published content. By means of a new real-world dataset, we show that the combination of features related to content, meta-data, and the temporal behavior leads to significantly improved predictions, compared to existing approaches which only consider features based on the historical popularity of the considered articles. Whereas traditionally linear regression is used for the application under study, we show that the more expressive gradient tree boosting method proves beneficial for predicting news popularity.
Keywords
IBCN, Online news, Popularity modeling, Popularity prediction, Regression, Feature engineering

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.64 MB
  • 7050 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 712.19 KB

Citation

Please use this url to cite or link to this publication:

MLA
Van Canneyt, Steven et al. “Modeling and Predicting the Popularity of Online News Based on Temporal and Content-related Features.” MULTIMEDIA TOOLS AND APPLICATIONS 77.1 (2018): 1409–1436. Print.
APA
Van Canneyt, S., Leroux, P., Dhoedt, B., & Demeester, T. (2018). Modeling and predicting the popularity of online news based on temporal and content-related features. MULTIMEDIA TOOLS AND APPLICATIONS, 77(1), 1409–1436.
Chicago author-date
Van Canneyt, Steven, Philip Leroux, Bart Dhoedt, and Thomas Demeester. 2018. “Modeling and Predicting the Popularity of Online News Based on Temporal and Content-related Features.” Multimedia Tools and Applications 77 (1): 1409–1436.
Chicago author-date (all authors)
Van Canneyt, Steven, Philip Leroux, Bart Dhoedt, and Thomas Demeester. 2018. “Modeling and Predicting the Popularity of Online News Based on Temporal and Content-related Features.” Multimedia Tools and Applications 77 (1): 1409–1436.
Vancouver
1.
Van Canneyt S, Leroux P, Dhoedt B, Demeester T. Modeling and predicting the popularity of online news based on temporal and content-related features. MULTIMEDIA TOOLS AND APPLICATIONS. Dordrecht: Springer; 2018;77(1):1409–36.
IEEE
[1]
S. Van Canneyt, P. Leroux, B. Dhoedt, and T. Demeester, “Modeling and predicting the popularity of online news based on temporal and content-related features,” MULTIMEDIA TOOLS AND APPLICATIONS, vol. 77, no. 1, pp. 1409–1436, 2018.
@article{8547204,
  abstract     = {As the market of globally available online news is large and still growing, there is a strong competition between online publishers in order to reach the largest possible audience. Therefore an intelligent online publishing strategy is of the highest importance to publishers. A prerequisite for being able to optimize any online strategy, is to have trustworthy predictions of how popular new online content may become. This paper presents a novel methodology to model and predict the popularity of online news. We first introduce a new strategy and mathematical model to capture view patterns of online news. After a thorough analysis of such view patterns, we show that well-chosen base functions lead to suitable models, and show how the influence of day versus night on the total view patterns can be taken into account to further increase the accuracy, without leading to more complex models. Second, we turn to the prediction of future popularity, given recently published content. By means of a new real-world dataset, we show that the combination of features related to content, meta-data, and the temporal behavior leads to significantly improved predictions, compared to existing approaches which only consider features based on the historical popularity of the considered articles. Whereas traditionally linear regression is used for the application under study, we show that the more expressive gradient tree boosting method proves beneficial for predicting news popularity.},
  author       = {Van Canneyt, Steven and Leroux, Philip and Dhoedt, Bart and Demeester, Thomas},
  issn         = {1380-7501},
  journal      = {MULTIMEDIA TOOLS AND APPLICATIONS},
  keywords     = {IBCN,Online news,Popularity modeling,Popularity prediction,Regression,Feature engineering},
  language     = {eng},
  number       = {1},
  pages        = {1409--1436},
  publisher    = {Springer},
  title        = {Modeling and predicting the popularity of online news based on temporal and content-related features},
  url          = {http://dx.doi.org/10.1007/s11042-017-4348-z},
  volume       = {77},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: