Abstract
Traditional design practice primarily relies on human designers' skills and knowledge for problem solving. With the advent of Large Language Models (LLMs), there is a significant possibility of leveraging the language processing capabilities to assist designers in increasing the speed, rigor, and effectiveness of various design activities. In the context of service design projects, we embarked on an investigation of utilizing LLMs to streamline labor-intensive tasks such as analyzing user research data more effectively. Through our investigation, we propose a mixed LLM-human approach in the Design Process, especially for qualitative data analysis. This paper discusses our observations from the investigation of leveraging LLMs for qualitative data analysis in a service design project and elaborates the proposed approach. We believe that these learnings hold broader relevance for the design discipline, empowering designers to delegate tedious design tasks to AI (LLMs), thus optimizing their workflow and productivity.
Keywords
llm; ai; design; creativity
DOI
https://doi.org/10.21606/drs.2024.789
Citation
Ganwani, S., Ratkal, S., Mahamuni, R., and Pathak, I. (2024) Synergizing human expertise with AI: The role of LLMs in user research, in Gray, C., Ciliotta Chehade, E., Hekkert, P., Forlano, L., Ciuccarelli, P., Lloyd, P. (eds.), DRS2024: Boston, 23–28 June, Boston, USA. https://doi.org/10.21606/drs.2024.789
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Research Paper
Included in
Synergizing human expertise with AI: The role of LLMs in user research
Traditional design practice primarily relies on human designers' skills and knowledge for problem solving. With the advent of Large Language Models (LLMs), there is a significant possibility of leveraging the language processing capabilities to assist designers in increasing the speed, rigor, and effectiveness of various design activities. In the context of service design projects, we embarked on an investigation of utilizing LLMs to streamline labor-intensive tasks such as analyzing user research data more effectively. Through our investigation, we propose a mixed LLM-human approach in the Design Process, especially for qualitative data analysis. This paper discusses our observations from the investigation of leveraging LLMs for qualitative data analysis in a service design project and elaborates the proposed approach. We believe that these learnings hold broader relevance for the design discipline, empowering designers to delegate tedious design tasks to AI (LLMs), thus optimizing their workflow and productivity.