Examining the Connection Between the Color Scheme of Event Announcement Images and View Counts on Social Media Through Machine Learning Models
DOI:
https://doi.org/10.52731/liir.v006.374Keywords:
CNN, SHAP, Machine Learning, Social MediaAbstract
In this study, we examined whether there is a relationship between the colors used in event announcement images and the number of views. We compared two machine learning models: a conventional model using event images, latitude/longitude, and titles as explanatory variables, and a proposed model incorporating the number of colors, representative HSV colors, latitude/longitude, and titles. The results showed that the proposed model performed similarly to the conventional model. Further analysis revealed that the number of colors and HSV values influenced the number of views. Therefore, it was revealed that the colors in event announcement images are related to the number of views.
References
Z. Li, X. Fang, O. Sheng, “A Survey of Link Recommendation for Social Networks: Methods, Theoretical Foundations, and Future Research Directions,” ACM Trans-actions on Management Information Systems, vol. 9, no. 1, 2018, pp. 1-26.
U. Shardanand, P. Maes, “Social information filtering: Algorithms for automating ‘word of mouth’,” In Proceedings of the SIGCHI conference on Human factors in computing systems, pp. 210-217, 1995.
Part 1: Special Feature: The Data-driven Economy and Social Transformation, Ministry of Internal Affairs and Communications, http://www.soumu.go.jp/johotsusintokei/whitepaper/ja/h29/html/nc121210.html.
D. Inoue and S. Matsumoto, “A View Count Prediction Method for Micro-Event Promotional Images Using CNN,” IEEJ Transactions on Electronics, Information and Systems, vol. 144, no. 9, 2024, pp. 942-954.
D. Inoue and S. Matsumoto, “Evaluating the Usefulness of View Count Prediction in a Local Information Sharing Service,” Proceedings of the 24th IEEE Hiroshima Section Student Symposium, TP-D-15, 2022, pp. 225-228.
D. Inoue and S. Matsumoto, “Click Count Prediction of Event Promotional Images Focusing on Title Information,” Proceedings of the 2023 IEEJ Conference on Elec-tronics, Information and Systems, GS4-5, 2023, pp. 1285-1290.
D. Inoue and S. Matsumoto, “A Design Classification Method for Event Promotional Images Using GMM,” Proceedings of the 90th Information Systems Research Meeting, IS-22-041, 2022, pp. 13-18.
K. Morishige, S. Matsumoto, “Relationship Between Color Schemes of Event An-nouncement Images and View Counts on Social Media Using GMM”, 16th Interna-tional Congress on Advanced Applied Informatics, DOI: 10.1109/IIAI-AAI 63651.2024.00107, 2024, pp. 562-567.
K. Morishige, D. Inoue, S. Matsumoto, “A Study on Increasing View Counts of Micro-Events on Social Media: Detecting the Relationship Between Color Schemes and View Counts,” Proceedings of the 98th Information Systems Research Meeting, IS-24-029, 2024, pp. 5-8.
K. Morishige, D. Inoue, S. Matsumoto, “A Study on Improving View Counts of Micro-Events on Social Media - Detecting the Relationship Between Color Schemes and View Counts -”, 30th International Symposium on Artificial Life and Robotics, OS16-1, 2025, pp. 1429-1432.
L. I. Labrecque, “Color research in marketing: Theoretical and technical consid-erations for conducting rigorous and impactful color research”, Psychology & Marketing, vol. 37, no. 7, 2020, pp. 855–863.
A. Krishna, “An integrative review of sensory marketing: Engaging the senses to affect perception, judgment and behavior”, Journal of Consumer Psychology, vol. 22, no. 3, 2012, pp. 332–351.
E. Shimoyama, K. Morishige, S. Matsumoto, “Effectiveness of Image Data as Explanatory Variables in Click Count Prediction Models for Local Information Sharing Services,” Proceedings of the 75th Joint Conference of the Chugoku Chapters of Institutes of Electrical and Information Engineers, R24-26-02, 2024.
D. Inoue and S. Matsumoto, “Click Count Prediction in a Local Information Sharing Service Using CNN Considering Micro-Event Information,” Proceedings of the 25th IEEE Hiroshima Section Student Symposium, TP-B-27, 2023, pp. 257–260.
K. He, X. Zhang, S. Ren, J. Sun. “Deep Residual Learning for Image Recognition,” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
