Abstract
Language functions as both a core element and the cognitive framework that supports the entire design process. However, the deep integration of Large Language Models (LLMs) is shifting the creative process from self- or human-to-human dialogue to human-AI conversation, requiring a careful examination of this emerging form of collaborative language. This study conducted an experiment on designer-AI collaboration. The goal was to explore the relationship between their collaborative activities, linguistic features, and co-creativity. By carefully coding activities and using the Linguistic Inquiry and Word Count (LIWC) method, we identified conversational features linked to different levels of creativity. These findings not only enhance understanding of the Human-AI collaborative design language but also offer important warnings and essential regulatory insights for designers engaging in co-creation with Textual GenAI.
Keywords
Human-AI Co-creation, Linguistic Features, Language, Collaborative activity
DOI
https://doi.org/10.21606/drs.2026.1275
Citation
Song, Y., Hu, Y., Zhou, Z., Deng, W., Du, X., and Bai, Y. (2026) Within the dialogue box: Exploring designer activities and linguistic features in collaboration with textual GenAI, in Simeone, L., Gray, C. M., Verhoeven, A., de Götzen, A., Bakırlıoğlu, Y., Zohar, H., Stead, M., and Buwert, P. (eds.), DRS2026: Edinburgh, 8–12 June, Edinburgh, United Kingdom. https://doi.org/10.21606/drs.2026.1275
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Included in
Within the dialogue box: Exploring designer activities and linguistic features in collaboration with textual GenAI
Language functions as both a core element and the cognitive framework that supports the entire design process. However, the deep integration of Large Language Models (LLMs) is shifting the creative process from self- or human-to-human dialogue to human-AI conversation, requiring a careful examination of this emerging form of collaborative language. This study conducted an experiment on designer-AI collaboration. The goal was to explore the relationship between their collaborative activities, linguistic features, and co-creativity. By carefully coding activities and using the Linguistic Inquiry and Word Count (LIWC) method, we identified conversational features linked to different levels of creativity. These findings not only enhance understanding of the Human-AI collaborative design language but also offer important warnings and essential regulatory insights for designers engaging in co-creation with Textual GenAI.