Advanced search
1 file | 1.06 MB Add to list

Predicting self‐declared movie watching behavior using Facebook data and information‐fusion sensitivity analysis

Author
Organization
Abstract
The main purpose of this paper is to evaluate the feasibility of predicting whether yes or no a Facebook user has self-reported to have watched a given movie genre. Therefore, we apply a data analytical framework that (1) builds and evaluates several predictive models explaining self-declared movie watching behavior, and (2) provides insight into the importance of the predictors and their relationship with self-reported movie watching behavior. For the first outcome, we benchmark several algorithms (logistic regression, random forest, adaptive boosting, rotation forest, and naive Bayes) and evaluate their performance using the area under the receiver operating characteristic curve. For the second outcome, we evaluate variable importance and build partial dependence plots using information-fusion sensitivity analysis for different movie genres. To gather the data, we developed a custom native Facebook app. We resampled our dataset to make it representative of the general Facebook population with respect to age and gender. The results indicate that adaptive boosting outperforms all other algorithms. Time- and frequency-based variables related to media (movies, videos, and music) consumption constitute the list of top variables. To the best of our knowledge, this study is the first to fit predictive models of self-reported movie watching behavior and provide insights into the relationships that govern these models. Our models can be used as a decision tool for movie producers to target potential movie-watchers and market their movies more efficiently.
Keywords
Management of Technology and Innovation, Strategy and Management, General Business, Management and Accounting, Information Systems and Management, Facebook, information-fusion, machine learning, movies, predictive models, social media, DATA ANALYTIC APPROACH, BOX-OFFICE, CHURN PREDICTION, ROTATION FOREST, REVIEWS, MODELS, CLASSIFIERS, SELECTION, TWEETS, AREA

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.06 MB

Citation

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

MLA
Bogaert, Matthias, et al. “Predicting Self‐declared Movie Watching Behavior Using Facebook Data and Information‐fusion Sensitivity Analysis.” DECISION SCIENCES, 2020, doi:10.1111/deci.12406.
APA
Bogaert, M., Ballings, M., Bergmans, R., & Van den Poel, D. (2020). Predicting self‐declared movie watching behavior using Facebook data and information‐fusion sensitivity analysis. DECISION SCIENCES. https://doi.org/10.1111/deci.12406
Chicago author-date
Bogaert, Matthias, Michel Ballings, Rob Bergmans, and Dirk Van den Poel. 2020. “Predicting Self‐declared Movie Watching Behavior Using Facebook Data and Information‐fusion Sensitivity Analysis.” DECISION SCIENCES. https://doi.org/10.1111/deci.12406.
Chicago author-date (all authors)
Bogaert, Matthias, Michel Ballings, Rob Bergmans, and Dirk Van den Poel. 2020. “Predicting Self‐declared Movie Watching Behavior Using Facebook Data and Information‐fusion Sensitivity Analysis.” DECISION SCIENCES. doi:10.1111/deci.12406.
Vancouver
1.
Bogaert M, Ballings M, Bergmans R, Van den Poel D. Predicting self‐declared movie watching behavior using Facebook data and information‐fusion sensitivity analysis. DECISION SCIENCES. 2020;
IEEE
[1]
M. Bogaert, M. Ballings, R. Bergmans, and D. Van den Poel, “Predicting self‐declared movie watching behavior using Facebook data and information‐fusion sensitivity analysis,” DECISION SCIENCES, 2020.
@article{8623833,
  abstract     = {The main purpose of this paper is to evaluate the feasibility of predicting whether yes or no a Facebook user has self-reported to have watched a given movie genre. Therefore, we apply a data analytical framework that (1) builds and evaluates several predictive models explaining self-declared movie watching behavior, and (2) provides insight into the importance of the predictors and their relationship with self-reported movie watching behavior. For the first outcome, we benchmark several algorithms (logistic regression, random forest, adaptive boosting, rotation forest, and naive Bayes) and evaluate their performance using the area under the receiver operating characteristic curve. For the second outcome, we evaluate variable importance and build partial dependence plots using information-fusion sensitivity analysis for different movie genres. To gather the data, we developed a custom native Facebook app. We resampled our dataset to make it representative of the general Facebook population with respect to age and gender. The results indicate that adaptive boosting outperforms all other algorithms. Time- and frequency-based variables related to media (movies, videos, and music) consumption constitute the list of top variables. To the best of our knowledge, this study is the first to fit predictive models of self-reported movie watching behavior and provide insights into the relationships that govern these models. Our models can be used as a decision tool for movie producers to target potential movie-watchers and market their movies more efficiently.},
  author       = {Bogaert, Matthias and Ballings, Michel and Bergmans, Rob and Van den Poel, Dirk},
  issn         = {0011-7315},
  journal      = {DECISION SCIENCES},
  keywords     = {Management of Technology and Innovation,Strategy and Management,General Business,Management and Accounting,Information Systems and Management,Facebook,information-fusion,machine learning,movies,predictive models,social media,DATA ANALYTIC APPROACH,BOX-OFFICE,CHURN PREDICTION,ROTATION FOREST,REVIEWS,MODELS,CLASSIFIERS,SELECTION,TWEETS,AREA},
  language     = {eng},
  pages        = {35},
  title        = {Predicting self‐declared movie watching behavior using Facebook data and information‐fusion sensitivity analysis},
  url          = {http://dx.doi.org/10.1111/deci.12406},
  year         = {2020},
}

Altmetric
View in Altmetric
Web of Science
Times cited: