Abstract
Addressing the risk of uncontrolled dissemination of AI deepfake videos in entertainment scenarios, this study constructs an explainable ensemble learning prediction framework from an entertainment computing perspective, systematically revealing the diffusion mechanisms of technology-enabled entertainment content. Guided by information ecosystem theory, the study first identifies nine core factors influencing deepfake video propagation through multidimensional feature decomposition. It innovatively proposes the RFECV-GA-PSO-RF hybrid feature selection algorithm to achieve efficient dimensionality reduction of entertainment computing features. Subsequently, the study employs a PSO-GA-XGBOOST ensemble model—fusing particle swarm optimization (PSO) and genetic algorithm (GA)—to achieve precise predictions of deepfake video propagation on real-world Chinese video platforms. This approach significantly outperforms existing models, demonstrating average improvements of 42.95% across four evaluation metrics (RMSE reduced to 1.230, MAPE reduced to 0.280, MAE reduced to 1.063, R² reaching 0.818). Finally, leveraging the interpretability of this predictive model, the study quantifies the importance of each feature and feature dimension. The proposed integrated prediction model not only provides novel predictive tools for the field of entertainment computing but also offers quantitative decision support for dissemination regulation and content ecosystem optimization in the era of intelligent entertainment, expanding the theoretical boundaries of interdisciplinary research in entertainment technology.
Similar content being viewed by others
Data availability
Data will be made available on request. If needed, please contact Jia Wang via email at wangjia1337@bupt.edu.cn.
References
Du, H. et al. Exploring collaborative distributed diffusion-based AI-generated content (AIGC) in wireless networks. IEEE Netw. 38 (3), 178–186 (2024).
Li, Z. et al. A survey on multimodal deepfake and detection techniques. J. Comput. Res. Dev. 60 (6), 1396–1416 (2023).
Mustak, M. et al. Deepfakes: Deceptions, mitigations, and opportunities. J. Bus. Res. 154, 113368 (2023).
He, K. et al. Cognitive Rashomon effect manufacturing: a case study of deepfake in russia-ukraine conflict. J. Mass. Soc. 1, 88–96 (2023).
Lee, Y. et al. To believe or not to believe: framing analysis of content and audience response of top 10 deepfake videos on YouTube. J. Cyberpsych Beh Soc. N. 24 (3), 153–158 (2021).
O’Donnell, N. Have we no decency? Section 230 and the liability of social media companies for deepfake videos, U. Ill. Law Rev. 2, 701–740 (2021).
Lasswell, H. D. The structure and function of communication in society. Comm. Ideas. 37 (1), 136–139 (1948).
Ni, Y. et al. Prediction of cultural UGC communication effectiveness from the perspective of multi-source heterogeneous data fusion: a combination modeling of GRA-PSO-WRF method. Manag Rev. 36 (11), 235–247 (2024).
Hsieh, J. K., Hsieh, Y. C. & Tang, Y. C. Exploring the disseminating behaviors of eWOM marketing: persuasion in online video. Electron. Commer. Res. 12 (2), 201–224 (2012).
Chaiken, S. Heuristic versus systematic information processing and the use of source versus message cues in persuasion. J. Pers. Soc. Psychol. 39 (5), 752–766 (1980).
Zhou, T., Liu, J. & Deng, S. Online knowledge video dissemination effects based on heuristic-systematic model. J. Mod. Inf. 44 (08), 61–68 (2024).
Fu, S., Su, Y. & Sun, J. Factors that influence the dissemination effects of short videos of refuting rumors based on heuristic-systematic model. J. Chn Soc. Sci. Tech. Inf. 43 (04), 457–469 (2024).
Hu, B. & Feng, C. Influencing factors of propagation effect of science short videos from a cognitive perspective. Stud. Sci. Sci. 41 (10), 1755–1764 (2023).
Ding, D. & Li, X. An empirical study on influencing factors of video dissemination of university library in bilibili. Libr. Inf. Serv. 67 (21), 63–72 (2023).
Cen, C. H. et al. Enhancing the dissemination of Cantonese Opera among youth via bilibili: a study on intangible cultural heritage transmission. Hum. Soc. Sci. Commun. 11 (1), 1038 (2024).
Petty, R. E. et al. The elaboration likelihood model of persuasion, Berkowitz L. advances in experimental social psychology 123–205 (academic, 1986).
Fu, S. & Cheng, Q. Research on the influencing factors of false short video dissemination from the perspective of content emotion: based on CAC and ELM dual models. Inf. Doc. Serv. 46 (02), 61–69 (2025).
Hou, Z. et al. A study on dissemination effect and influencing factors of short health education videos. Chn J. Health Educ. 40 (10), 913–918 (2024).
Liu, J. F., Lu, C. Y. & Lu, S. J. H. Research on the influencing factors of audience popularity level of COVID-19 videos during the COVID-19 pandemic. Healthcare 9 (9), 1159 (2021).
Ma, X. et al. Video popularity prediction model based on attention and neural network. J. Hefei Univ. Technol. Nat. Sci. 46 (11), 1472–1478 (2023).
Zhong, Z. et al. Modeling dynamics of online short video popularity based on Douyin platform. J. Univ. Electron. Sci. Technol. China. 50 (05), 774–781 (2021).
Brewer, S. M., Kelley, J. M. & Jozefowicz, J. J. A blueprint for success in the US film industry. Appl. Econ. 41 (5), 589–606 (2009).
Zhang, W. & Skiena, S. S. Improving Movie Gross Prediction through News Analysis,2009 IEEE/WIC/ACM Int. Conf. on Web Intel. WI 2009 Milan Italy September 2009 Main Conference Proceedings 15–18. (2009).
Dellarocas, C., Zhang, X. M. & Awad, N. F. Exploring the value of online product reviews in forecasting sales: The case of motion pictures. J. Interact. Mark. 21(4), 23–45 (2007).
Cho, M., Jeong, D. & Park, E. Predicting popularity of short-form videos using multi-modal attention mechanisms in social media marketing environments. J. Retail Consum. Serv. 78, 103778 (2024).
Wu, W. et al. Deep attention video popularity prediction model fusing content features and Temporal information. J. Comput. Appl. 41 (7), 1878–1884 (2021).
Li, J., Guan, H. & Zhang, S. Modeling on playback volume prediction of self-produced programs of Chinese video websites. J. Inf. Commun. 24 (6), 7–20 (2017).
Zhu, H. et al. Study of short video popularity prediction based on network representation learning. J. Chn Soc. Sci. Tech. Inf. 43 (09), 1105–1115 (2024).
Lin, Y. T., Yen, C. C. & Wang, J. S. Video popularity prediction: an autoencoder approach with clustering. IEEE Access. 8, 129285–129299 (2020).
Halim, Z., Hussain, S. & Ali, R. H. Identifying content unaware features influencing popularity of videos on youtube: A study based on seven regions,Expert. Syst. Appl. 206, 117836 (2022).
Sangwan, N. & Bhatnagar, V. A framework for video popularity forecast utilizing metaheuristic algorithms. Arab. J. Sci. Eng. 47 (2), 2077–2094 (2022).
Chang, N. et al. An empirical study on the trigger mechanism of public opinion communication of hot events in social media. Inf. Sci. 41 (11), 120–127 (2023).
Dou, Y. et al. Research on the influence of dissemination and interaction of public security affairs Douyin accounts based on information ecology theory and algorithm recommendation. Oper. Res. Manage. Sci. 33 (5), 9–15 (2024).
Xu, X. & Zhao, Z. Research on demand characteristics and participation behavior of intangible cultural heritage information of short video users——taking Huangmei Opera short video online review as an example. J. Mod. Inf. 42 (8), 74–84 (2022).
Wang, C. & Mang, L. How government short videos gain viral impact: a content analysis of government Douyin accounts. E-Gov 7, 31–40 (2019).
Huang, C. The development status and trend of short videos under the integration background. Front 23, 40–47 (2017).
Welbourne, D. & Grant, W. Science communication on youtube: factors that affect channel and video popularity. Public. Underst. Sci. 25 (6), 706–718 (2016).
Zhao, L. The social construction of algorithmic practice: take an information distribution platform as an example. Sociol. Stud. 37 (4), 23–44 (2022).
Yang, D., Li, S. & Cong, Y. Research on influencing factors of transmission effect of reading promotion short videos on TikTok. Res. Libr. Sci. 23, 34–44 (2021).
Liu, G. & Wang, X. The influence of title features on the effect of digital media content communication——based on an empirical study of WeChat official accounts title in news commentary. J. Commun. Rev. 73 (6), 29–39 (2020).
Kui, J., Wang, L. & Liu, Y. A study on factors influencing users’ book purchase intentions via short videos. Chn Publ J. 6, 8–14 (2020).
Zhang, Y. et al. Empirical study on influencing factors of communication effect of scientific journal video on bilibili. Chn J. Sci. Tech. Period. 35 (08), 1125–1133 (2024).
Shen, H. et al. Research on the dissemination effectiveness of emergency knowledge short videos:an analysis based on different types of publishers,Inf. Stud. Theor. Appl. 47 (11), 101–110 (2024).
Ning, H. & Yang, W. Empirical analysis of factors influencing the communication effectiveness of major public health emergencies: a case study of health-related government accounts on Douyin. Mod. Commun. 43 (1), 147–151 (2021).
Meng, S. et al. Research on the impact of COVID-19 science information dissemination on social media and the factors influencing the choice of crisis coping strategies:an empirical analysis based on popular micro-blog texts of scientists’ groups. Libr. Inf. Serv. 66 (13), 91–101 (2022).
Liu, C., Chen, M. & Yi, L. Information features extraction and the correlation calculation of the deep fake videos. J. Intell. 43 (8), 92–101 (2024).
Jiang, J. & Wang, W. Research on government Douyin for public opinion of public emergencies: comparison with government microblog. J. Intell. 39 (1), 100–106 (2020).
Yang, H., Li, X. & Hu, Z. Survey of deepfake face generation and detection technologies. J. Huazhong Univ. Sci. Technol. 53 (05), 85–103 (2025).
Krippendorff, K. Agreement and information in the reliability of coding. Commun. Methods Meas. 5 (2), 93–112 (2011).
Chen, W. & Zhou, Y. An empirical study on factors influencing dissemination effect of short videos in popular science journals in china: focusing on 50 Chinese outstanding popular science journals in 2020. Chn J. Sci. Tech. Period. 34 (12), 1616–1622 (2023).
Acknowledgements
This research was funded by the Social Science Foundation of Beijing, China(NO.25JCC128).
Author information
Authors and Affiliations
Contributions
Xiaofei Ma: Writing - review & editing, Writing - original draft, Conceptualization.Jia Wang: Writing - review & editing, Writing - original draft, Validation, Methodology, Conceptualization.Enyu Ji: Writing - review & editing, Conceptualization.Zhongyu Wang: Writing - review & editing, Conceptualization.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Ma, X., Wang, J., Ji, E. et al. Prediction model for the dissemination of AI-generated deepfake videos in the intelligent entertainment paradigm. Sci Rep (2026). https://doi.org/10.1038/s41598-025-34789-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34789-4
