The Journal of Society for e-Business Studies (한국전자거래학회지)

Society for e-Business Studies (한국전자거래학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Box Office Prediction Using the Image Characteristics of Advertising Posters in Performing Arts

공연예술에서 광고포스터의 이미지 특성을 활용한 딥러닝 기반 관객예측

  • Received : 2021.01.14
  • Accepted : 2021.04.19
  • Published : 2021.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

공연예술 기관에서의 공연에 대한 흥행 예측은 공연예술 산업 및 기관에서 매우 흥미롭고도 중요한 문제이다. 이를 위해 출연진, 공연장소, 가격 등 정형화된 데이터를 활용한 전통적인 예측방법론, 데이터마이닝 방법론이 제시되어 왔다. 그런데 관객들은 공연안내 포스터에 의하여 관람 의도가 소구되는 경향이 있음에도 불구하고, 포스터 이미지 분석을 통한 흥행 예측은 거의 시도되지 않았다. 그러나 최근 이미지를 통해 판별하는 CNN 계열의 딥러닝 방법이 개발되면서 포스터 분석의 가능성이 열렸다. 이에 본 연구의 목적은 공연 관련 포스터 이미지를 통해 흥행을 예측할 수 있는 딥러닝 방법을 제안하는 것이다. 이를 위해 KOPIS 공연예술 통합전산망에 공개된 포스터 이미지를 학습데이터로 하여 Pure CNN, VGG-16, Inception-v3, ResNet50 등 딥러닝 알고리즘을 통해 예측을 수행하였다. 또한 공연 관련 정형데이터를 활용한 전통적 회귀분석 방법론과의 앙상블을 시도하였다. 그 결과 흥행 예측 정확도 85%를 상회하는 높은 판별 성과를 보였다. 본 연구는 공연예술 분야에서 이미지 정보를 활용하여 흥행을 예측하는 첫 시도이며 본 연구에서 제안한 방법은 연극 외에 영화, 기관 홍보, 기업 제품 광고 등 포스터 기반의 광고를 하는 영역으로도 적용이 가능할 것이다.

Keywords

Acknowledgement

This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea(NRF-2020S1A3A2A02093277).

References

  1. Baltruschat, I. M., Nickisch, H., Grass, M., Knopp, T., and Saalbach, A., "Comparison of Deep Learning Approaches for Multi-label Chest X-ray Classification," Scientific reports, Vol. 9, No. 1, pp. 1-10, 2019. https://doi.org/10.1038/s41598-018-37186-2
  2. Chae, S. H., "A Study on the Awareness of and Preference for Make-up Images in Performance Posters and the Intention to Attend a Performance," Oriental Arts, Vol. 32, pp. 359-389, 2016.
  3. Cho, Y. H., Park, Y. S., and Kim, H. J., "Changes in Review Length based on the Popularity of Movies using Big Data," Journal of The Korea Contents Association, Vol. 18, No. 5, pp. 367-375, 2018. https://doi.org/10.5392/JKCA.2018.18.05.367
  4. Chon, B. S. and Yi, J. Y., "The effects of domestic and global movie rating services on economic performances of movies in korea," Journal of Communication Science, Vol. 19, No. 4, pp. 227-253, 2019. https://doi.org/10.14696/jcs.2019.12.19.4.226
  5. Chon, B. S., Park, S. B., and Jo, A. R., "The effects of movie stars on box-office performances," The Journal of Image and Cultrual Contents, Vol. 18, pp. 363-389, 2019 https://doi.org/10.24174/jicc.2019.10.18.363
  6. de Rooij, P. and Bastiaansen, M., "Understanding and measuring consumption motives in the performing arts," The Journal of Arts Management, Law, and Society, Vol. 47, No. 2, pp. 118-135, 2017. https://doi.org/10.1080/10632921.2016.1259132
  7. Gozuacik, N. and Sakar, C. O., "Turkish movie genre classification from poster images using convolutional neural networks," In 2019 11th International Conference on Electrical and Electronics Engineering(ELECO), pp. 930-934, 2019.
  8. Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., and Lew, M. S., "Deep learning for visual understanding: a review," Neurocomputing, Vol. 187, pp. 27-48, 2016. https://doi.org/10.1016/j.neucom.2015.09.116
  9. He, K., Zhang, X., Ren, S., and Sun, J., "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.
  10. Im, E. K. and Seo, I. S., "Study of pictorial digital image shown on the movie posters-focused on top 10 national films shown in between 2003-2012," Journal of Digital Design, Vol. 12, No. 3, pp. 497-506, 2012. https://doi.org/10.17280/jdd.2012.12.3.047
  11. Jang, S., Wi, J., and Kim, Y., "Korean movie genre classification based on poster images with multi-label training using CNN," Proceedings of HCIK 2019, pp. 746-749, 2019.
  12. Jeong, C. M. and Min, D. K., "A Study on the Performance Evaluation of Machine Learning for Predicting the Number of Movie Audiences," The Jounal of Society for e-Business Studies, Vol. 25, No.2 , pp. 49-63, 2020.
  13. Joo, J., Steen, F. F., and Zhu, S. C., "Automated facial trait judgment and election outcome prediction: social dimensions of face," In Proceedings of the IEEE international conference on computer vision, pp. 3712-3720, 2015.
  14. Kim, B. K. and Lim, C. W., "Prediction of movie audience numbers using hybrid model combining GLS and Bass models," The Korean Journal of Applied Statistics, Vol. 31, No. 4, pp. 447-461, 2018. https://doi.org/10.5351/KJAS.2018.31.4.447
  15. Kim, B. S., "Comparison of factors predicting theatrical movie success: focusing on the classification by the release type and the length of run," Korean Journal of Journalism and Communication Studies, Vol. 53, No. 1, pp. 257-287, 2009.
  16. Kim, H. Y. and Seo, D. H., "A topic modeling approach to the analysis of domestic performance," Official Journal of Korean Society of Dance Science, Vol. 36, No. 3, pp. 99-111, 2019.
  17. Kim, S. J., Choi, I. S., and Seok, S. M., "Comparative analysis of movie poster colors according to genre -On thriller/mystery, comedy & melo/romance movies (2010-2015)," Journal of The Korean Society of Illustration Research, Vol. 18, No. 53, pp. 33-42, 2017.
  18. Kim, S. Y., Lim, S. H., and Jung, Y. S., "A comparison study of the determinants of performance of motion pictures: art film vs. commercial film," The Journal of the Korea Contents Association, Vol. 10, No. 2, pp. 381-393, 2010. https://doi.org/10.5392/JKCA.2010.10.2.381
  19. Kim, S. Y. and Yi, E. S., "A case study on big data analysis of performing arts consumer for audience development," Journal of the Korea Academia-Industrial cooperation Society, Vol. 18, No. 12, pp. 286-299, 2017.
  20. Kim, S. M., Kim, J. Y., and Choi, M. C., "The study of the spectating factors and satisfactions effect on the re-spectate Intention," The Journal of Management, Vol. 32, pp. 23-38, 2011.
  21. Kim, T. H. and Shin, H. D., "The impacts of theme, genre, and existence of originals on the number of visitors of children performance: Focusing on the interaction effect of school periods," Journal of the Korea Academia-Industrial cooperation Society, Vol. 14, No. 10, pp. 4762-4768, 2013. https://doi.org/10.5762/KAIS.2013.14.10.4762
  22. Kim, Y. H. and Hong, J. H., "A study for the development of motion picture box-office prediction model," Communications for statistical applications and methods, Vol. 18, No. 6, pp. 859-869, 2011. https://doi.org/10.5351/CKSS.2011.18.6.859
  23. Kim, S. H. and Han, J. M., "An analysis of motion picture box office performance : focusing on korean movies released in 2012," Journal of Social Science, Vol. 53, No. 1, pp. 191-214, 2014.
  24. Kwon, H. I., Jung, S. G., and Choi, Y. S., "Effects of factors of purchase intention to viewing performance by audience type," The Journal of the Korea Contents Association, Vol. 15, No. 2, pp. 139-150, 2015. https://doi.org/10.5392/JKCA.2015.15.02.139
  25. Kwon, S. J., "Factors influencing cinema success: using news and online Rates," Review of Cultural Economics, Vol. 17, No. 1, pp. 35-55, 2014.
  26. Lee, E. M. and Chung, Y. K., "The study of the revitalization of performing arts audiences: focused on the obstructive factor and remedy for performing arts," Journal of Arts Management and Policy, Vol. 42, pp. 211-247, 2017.
  27. Lee, J. H. and Kim, Y. J., "A study on the factors in box-office of the audience-driven attributes," Journal of the Korea Entertainment Industry Association, Vol. 7, No. 1, pp. 1-9, 2013.
  28. Lee, J. K., Choi, Y. G., Jung, E. H., Jo, J. S., Ko, H. J., and Jo, H., "The effect of buzz volume on success of movie," The Journal of Internet Electronic Commerce Research, Vol. 19, No. 1, pp. 211-221, 2019.
  29. Panahi, M., Sadhasivam, N., Pourghasemi, H. R., Rezaie, F., and Lee, S., "Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression(SVR)," Journal of Hydrology, Vol. 588, pp. 125033, 2020. https://doi.org/10.1016/j.jhydrol.2020.125033
  30. Park, S. and Shim, H., "Movie poster classification into genres via convolutional neural network," Proceedings of the The Korean Institute of Information Scientists and Engineers, pp. 890-892, 2017.
  31. Park, S. H., Song, H. J., and Jung, W. K., "The determinants of motion picture box office performance: evidence from korean movies released in 2009-2010," Journal of Communication Science, Vol. 11, pp. 231-258, 2011.
  32. Rhine, A. S. and Murnin, P. M., "Day, duration, and start time: are the arts providing what their audiences require?," Arts and the Market, Vol. 8, No. 1, pp. 19-29, 2018. https://doi.org/10.1108/AAM-12-2017-0027
  33. Saif, M. A., Medvedev, A. N., Medvedev, M. A., and Atanasova, T., "Classification of online toxic comments using the logistic regression and neural networks models," In AIP conference proceedings, AIP Publishing LLC, Vol. 2048, No. 1, pp. 060011, 2018.
  34. Simonyan, K. and Zisserman, A., "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
  35. Song, E. A., "A study of the factors explaining the long-run theatre," Journal of the Korea Entertainment Industry Association, pp. 132-136, 2013.
  36. Sudharshan, P. J., Petitjean, C., Spanhol, F., Oliveira, L. E., Heutte, L., and Honeine, P., "Multiple instance learning for histopathological breast cancer image classification," Expert Systems with Applications, Vol. 117, pp. 103-111, 2019. https://doi.org/10.1016/j.eswa.2018.09.049
  37. Szegedy et al., "Going deeper with convolutions," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015.
  38. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z., "Rethinking the inception architecture for computer vision," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
  39. Yi, H. C., "Examining current challenges of Korean movie posters and seeking improvements for changes -Referencing the Hollywood movie poster production system-," Journal of Communication Design, Vol. 53, pp. 252-263, 2015.
  40. Yoo, M. H. and Kim, J. W., "A Study on the factors influencing satisfaction of the play audience: focusing on the Influence of others," Journal of Arts and Cultural Management, Vol. 10, No. 2, pp. 29-58, 2017.
  41. Yoon, J. W., Jeon, J. W., and Park, K. S., "Effects of font fit and familiarity on moviegoer's attitudes and intentions," Media and Performing Arts, Vol. 9, No. 1, pp. 1-28, 2014.
  42. Yu, J. P. and Lee, E. H., "A model of predictive movie 10 million spectators through big data analysis," The Korea Journal of BigData, Vol. 3, No. 1, pp. 63-71, 2018. https://doi.org/10.36498/KBIGDT.2018.3.1.63
  43. Zhang, K., Zhang, Z., Li, Z., and Qiao, Y., "Joint face detection and alignment using multitask cascaded convolutional networks," IEEE Signal Processing Letters, Vol. 23, No. 10, pp. 1499-1503, 2016. https://doi.org/10.1109/LSP.2016.2603342