Cross-Cultural Symbolic Drift in Algorithmic Portraiture: A Case Study of Edmond de Belamy

DOI

10.2991/978-2-38476-511-9_62How to use a DOI?

Keywords

Art semiotics; Generative adversarial networks (GANs); Cultural diversity; Digital humanities

Abstract

Within the framework of “digital technology enabling cultural diversity,” this paper takes the GAN-generated portrait Edmond de Belamy as a case study to examine how generative algorithms reshape visual symbols. By constructing a triadic model of Signifier–Signified–Algorithm and comparing multimodal outputs with Chinese and Western portrait conventions, the study finds that GANs trained on regionally imbalanced datasets tend to retain high-frequency Western elements (e.g., drapery, top lighting) while omitting or distorting over 80% of East Asian ceremonial symbols, leading to stylistic convergence and cultural marginalization. In response, the paper proposes a multi-level strategy: stratified sampling by region/era/subject, expanded cultural-symbol metadata, a three-tier authorship structure (Human–Machine–Community), and a closed-loop diversity audit system. These measures offer a verifiable semiotic approach to addressing cultural bias in AI-generated art and sustaining the digital transmission of folk and ethnic traditions.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, 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 license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ziwei Liu
AU  - Kuiying Zhao
PY  - 2025
DA  - 2025/12/31
TI  - Cross-Cultural Symbolic Drift in Algorithmic Portraiture: A Case Study of Edmond de Belamy
BT  - Proceedings of the 7th International Conference on Literature, Art and Human Development (ICLAHD 2025)
PB  - Atlantis Press
SP  - 545
EP  - 551
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-511-9_62
DO  - 10.2991/978-2-38476-511-9_62
ID  - Liu2025
ER  -