Electrotechnical and Computer Engineering
Vol. 35 No. 06 (2020): Proceedings of the Faculty of Technical Sciences
PREDICTING WEEKEND FILM BOX OFFICE
Abstract
This paper presents a study about predicting weekend film box office. The dataset that was made and described in the paper was taken from various relevant websites and from one scientific paper. Box office was predicted based on many attributes, one of which is an attribute that speaks of interest of public for a film based on their gender. That attribute was made when the synopsis of the film was run through NLP techniques, logistic regression, SVM and k-NN. The problem of predicting box office was approached with regression and classification models.
References
[1] Quader, N., Gani, M. O., Chaki, D., & Ali, M. H. (2017, December). A machine learning approach to predict movie box-office success. In 2017 20th International Conference of Computer and Information Technology (ICCIT) (pp. 1-7). IEEE.
[2] Sharda, R., & Delen, D. (2006). Predicting box-office success of motion pictures with neural networks. Expert Systems with Applications, 30(2), 243-254.
[3] Cook, C., Cunningham, B., Reading, E., Sedgewick, M., & Tilcock, K. Predicting Blockbuster Success.
[4] Hoang, Q. (2018). Predicting movie genres based on plot summaries. arXiv preprint arXiv:1801.04813.
[5] Song, J., & Han, S. (2013). Predicting gross box office revenue for domestic films. Communications for Statistical Applications and Methods, 20(4), 301-309.
[6] Wühr, P., Lange, B. P., & Schwarz, S. (2017). Tears or fears? Comparing gender stereotypes about movie preferences to actual preferences. Frontiers in psychology, 8, 428.