Predicting Emerging Art Styles in AI-Generated Artworks

Authors

  • Willy Willyem IBPTI

DOI:

https://doi.org/10.63017/jdsi.v2i2.99

Keywords:

AI-Generated Artworks, Algorithm, Art style, classification, predicting

Abstract

The development of artificial intelligence (AI) technology has brought significant changes in various fields, including the arts. AI-generated art is no longer just a technical experiment, but has evolved into a recognized artistic medium, creating new opportunities in the exploration of creativity and aesthetics. This study evaluates the prediction of aesthetic trends that develop in artistic creativity using the analysis of artwork datasets generated by Artificial Intelligence (AI) based on Machine Learning. In the digital age, AI has become an essential tool in art exploration, producing works with unique styles, techniques, and aesthetics. The study aims to understand the aesthetic patterns and dynamics that emerge from AI artwork. The results of the research obtained can be seen that the random tree model is an appropriate algorithm in making predictions. Through this approach, this article not only contributes to art and technology literature but also provides insight into how the relationship between humans and AI can shape the contemporary art landscape. This research is expected to be the basis for the development of more inclusive and creative AI technology in the future.

References

A. Purnomo. (2015). “Creativity in Fine Arts: Aesthetic and Cultural Perspectives” . Publisher Andi.

S. Ali., et al. (2021). “Children as creators, thinkers, and citizens in an AI-driven future”. Computers and Education: Artificial Intelligence.

Helena Sarin. (2019). “Exploring AI-generated aesthetics. Digital Creativity”, 30(1), 57-68.

K. Darling. (2015). “Who’s Johnny? Anthropomorphic framing in human-robot interaction”. PloS One, 10(3). Bird yok

A. Elgammal. et al. (2017). “CAN: Creative Adversarial Networks”. arXiv preprint arXiv:1706.07068.

R. Blanquero, E. Carrizosa, P. Ramírez-Cobo, and M. R. Sillero-Denamiel, “Variable selection for Naïve Bayes classification,” Comput. Oper. Res., Vol. 135, 2021, Doi: 10.1016/j.kar.2021.105456.

S. Karayev., et al. (2014). “Recognizing image style”. arXiv preprint arXiv:1311.3715.

P. Cunningham and S. J. Delany, “Random Tree-A Tutorial,” ACM Computing Surveys, vol. 54, no. 6. 2021. doi:10.1145/3459665.

A. McCosker & R. Wilken. (2020). “Machine Vision and Aesthetic Automation”. Media International Australia, 176(1), 99-113.

D. Okulov. (2022). “Exploring AI-generated art tools: Craiyon and DALL-E”. Journal of Digital Art Research, 12(3), 45-60.

M. Sabatelli. et al. (2022). “Understanding and Creating Art with AI”. ACM Transactions on Multimedia Computing, 18(2), 66.

P. Seele., & J. Schultz. (2022). “Disinformation and AI ethics”. International Journal for Multidisciplinary Research, 4(4), 12-20.

R. Wilken., et al. (2020). “Future aesthetics in digital media”. Digital Media Review, 15(3), 55-77.

X. Zhang & S. Zhu. (2021). “Art generation and the future of creative machines”. Artificial Intelligence Review, 55(1), 23-47.

W. E. Nurjanah (2021). “Integration of Traditional Arts and AI: A Case Study in Indonesia”. Journal of Arts and Culture of the Archipelago.

Downloads

Published

2024-08-01

How to Cite

[1]
W. Willyem, “Predicting Emerging Art Styles in AI-Generated Artworks”, Data Science Insights, vol. 2, no. 2, pp. 89–95, Aug. 2024.