Abstract
This study explores the potential of generative artificial intelligence (AI) to reveal and compare morphological characteristics in chair design across four cultural contexts. Using ChatGPT-4o, 200 chair images were generated and classified into 31 form-related categories, with both human evaluators and CLIP models conducting comparative analyses. Thirteen categories exhibited significant cross-cultural variation, uncovering not only recognized design tendencies but also previously overlooked features. Beyond classification, the findings highlight AI’s role as a human-centered partner in design education and evaluation. By providing objective and reproducible assessments, AI augments human observation, fosters cultural awareness, and supports transparent cross-cultural collaboration. Rather than replacing judgment, it serves as a cooperative tool that enhances perception, stimulates creativity, and contributes to identity formation in design. AI thus emerges as both an amplifier of human insight and a catalyst for more inclusive, con textually sensitive design practices.
Keywords
Chair; Generative AI; Human-centered; Chat GPT-4o
DOI
https://doi.org/10.21606/iasdr.2025.1091
Citation
Sakai, K., Ito, S.,and Bao, S.(2025) What Do AI-Generated Chairs Look Like? -A Comparative Study of Chair Across Four Countries-, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.1091
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 4 - Human-Centered AI
What Do AI-Generated Chairs Look Like? -A Comparative Study of Chair Across Four Countries-
This study explores the potential of generative artificial intelligence (AI) to reveal and compare morphological characteristics in chair design across four cultural contexts. Using ChatGPT-4o, 200 chair images were generated and classified into 31 form-related categories, with both human evaluators and CLIP models conducting comparative analyses. Thirteen categories exhibited significant cross-cultural variation, uncovering not only recognized design tendencies but also previously overlooked features. Beyond classification, the findings highlight AI’s role as a human-centered partner in design education and evaluation. By providing objective and reproducible assessments, AI augments human observation, fosters cultural awareness, and supports transparent cross-cultural collaboration. Rather than replacing judgment, it serves as a cooperative tool that enhances perception, stimulates creativity, and contributes to identity formation in design. AI thus emerges as both an amplifier of human insight and a catalyst for more inclusive, con textually sensitive design practices.