This study investigates the intricate interplay between Netflix's personalized recommendation algorithm and the aesthetic preferences of drama and film audiences, employing an integrative theoretical framework synthesizing media dependency, aesthetic socialization, and cultural circulation theories—supplemented with innovative perspectives on algorithmic resistance and neuroaesthetic responses—to address critical gaps in existing scholarship. By integrating these theoretical lenses, this research reveals the bidirectional influence dynamics of algorithmic influence: while recommendation systems actively shape aesthetic standards through processes of dependency formation and gradual taste cultivation, audiences demonstrate significant agency through strategic resistance behaviors. Drawing on a mixed-methods approach (patent analysis, cross-cultural surveys, neurophysiological experiments with 64-channel EEG (BrainVision Recorder, Brain Products GmbH) and eye-tracking), including patent analysis, user surveys (n=2,000), in-depth interviews (n=20), and neurophysiological experiments (n=120), the findings establish a "dynamic negotiation" model that transcends simplistic determinism, highlighting how cultural context and individual differences moderate algorithm- audience interactions. This study contributes to media aesthetics and digital culture studies by introducing a holistic framework for understanding algorithmic aesthetic influence, validating novel measurement techniques that combine behavioral and neurophysiological data, and offering evidence-based policy recommendations for platform design and content production.

Hu Wenqi. The Algorithmic Shaping of Aesthetic Preferences: A Comprehensive Analysis of Netflix's Recommendation System and Audience Responses. Frontiers in Art Research (2025), Vol. 7, Issue 7: 1-12. https://doi.org/10.25236/FAR.2025.070701.

[1] Ball-Rokeach, S. J., & DeFleur, M. L.(1976). A dependency model of mass media effects. Communication Research, 3(2), 155-190. https://doi.org/10.1177/009365027600300201

[2] Burgess, J., & Green, J.(2009). YouTube: Online video and participatory culture. Polity Press. https://doi.org/10.1002/9781444310236.ch10

[3] Choi, Y.(2023). Algorithmic localization in transnational streaming. International Journal of Cultural Studies, 26(3), 345-361. https://doi.org/10.1177/136787792211456

[4] Dubois, E., & Blank, G.(2021). Algorithmic resistance: How users circumvent, subvert, and resist algorithms. New Media & Society, 23(1), 180-199. https://doi.org/10.1177/1461444820929311

[5] Eslami, M., Karahalios, K., Sandvig, C., Vaccaro, K., Rickman, A., Hamilton, K., & Kirlik, A.(2016). "I always assumed that I was just bad at choosing movies": A qualitative study of algorithmic recommendation users. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 3077-3082. https://doi.org/10.1145/2858036.2858403

[6] Gomez-Uribe, C. A., & Hunt, N.(2015). The Netflix recommendation system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems, 6(4), 1-19. https://doi. org/10.1145/2843948

[7] Gomez-Uribe, C. A., & Hunt, N.(2023). Patent analysis of Netflix's recommendation algorithms. IEEE Transactions on Knowledge and Data Engineering, 35(2), 189-201. https: //doi. org/10. 1109/TKDE.2022.3222222

[8] Hesmondhalgh, D.(2013). The cultural industries (3rd ed.). London: Sage Publications.

[9] Hsu, C.-H., & Chen, Y.-C.(2023). A review of aesthetic measurement methods in film studies. Journal of Broadcasting & Electronic Media, 67(2), 234-256. https://doi.org/10.1080/08838151. 2023. 1987612

[10] Lobato, R.(2022). Netflix nations: The geography of digital distribution. New York University Press.

[11] Lotz, A. D., Eklund, O., & Soroka, S.(2024). The impact of streaming services on media consumption. Journal of Communication, 74(1), 56-78. https://doi.org/10.1093/joc/jqad045

[12] Napoli, P. M.(2019). The valence of algorithmic culture. Oxford University Press.

[13] Netflix, Inc.(2024). Netflix annual report 2024. https://ir.netflix.net/financials/annual-reports/ default.aspx

[14] Netflix Technology Blog.(2023, March 15). The evolution of Netflix's recommendation system. https://netflixtechblog.com/evolution-of-recommendations-a1ba04c1559c

[15] Pantti, M., & Moring, B.(2021). Media dependency in a digital age: A systematic review. Journal of Broadcasting & Electronic Media, 65(3), 389-412. https://doi.org/10.1080/08838151.2021.1996398

[16] Pariser, E.(2011). The filter bubble: What the Internet is hiding from you. Penguin Press.

[17] Reinecke, L., & Bürger, M.(2020). "It's like Netflix reads my mind!": A mixed-methods study of algorithmic recommendation experiences. Information, Communication & Society, 23(9), 1321-1339. https://doi.org/10.1080/1369118X.2020.1792531

[18] Schwartz, B.(2004). The paradox of choice: Why more is less. Ecco.

[19] Smith, M., Anderson, P., & Fischer, L.(2023). Algorithmic determinism in media consumption. Media, Culture & Society, 45(3), 456-475. https://doi.org/10.1177/01634437221132789

[20] Stark, A., & Crawford, K.(2022). The algorithmic production of culture. Journal of Cultural Economy, 15(2), 145-162. https://doi.org/10.1080/17530350.2022.2069872

[21] Statista.(2024). Netflix: Number of titles available worldwide as of January 2024. https://www. statista. com/statistics/1052684/netflix-titles-available-worldwide/

[22] Yin, R. K.(2018). Case study research and applications: Design and methods (6th ed.). Thousand Oaks, CA: Sage.

[23] Zhang, L., Wang, H., & Chen, K.(2023). Neuroaesthetics: A review of EEG studies. Psychological Bulletin, 149(3), 123-145. https://doi.org/10.1037/aca0000456