Research on Ideation Process and Design Productivity of ChatGPT Based on LASSO and Linkography | IEEE Conference Publication | IEEE Xplore

Research on Ideation Process and Design Productivity of ChatGPT Based on LASSO and Linkography


Abstract:

In design, good ideas are the source of a designer’s creativity. With the development of artificial intelligence, large language models (LLMs) represented by ChatGPT show...Show More

Abstract:

In design, good ideas are the source of a designer’s creativity. With the development of artificial intelligence, large language models (LLMs) represented by ChatGPT shows excellent conversational and creative reasoning capabilities. However, we still know very little about the design ideation process and its performance in terms of productivity. In this paper, we propose a representation of the design ideation process based on NLP. On this basis, referring to LASSO and linkography method, we propose a DCLASSO model to calculate the interconnections between design moves in protocol analysis. In the subsequent experiment, we take the design protocols generated by ChatGPT as the experimental sample to verify the proposed model. Finally, with the generated linkographs, the characteristics of ChatGPT and human designers are analyzed and compared from aspects of design ideation process and design productivity.
Date of Conference: 16-17 December 2023
Date Added to IEEE Xplore: 15 April 2024
ISBN Information:

ISSN Information:

Conference Location: Hangzhou, China
No metrics found for this document.

I. Introduction

In design, good ideas determine the degree of creativity. A creative product in any field must be full of some good ideas that are unique to human designers. With the development of artificial intelligence, AI agents have begun to move from generating stimuli that support creative ideas to directly generating creative contents and products[1]. Recently, large language models (LLMs), such as ChatGPT, pre-trained on a large corpus of text data, have shown excellent performance on a wide range of NLP tasks, including language translation, text summarization, and question answering. Unlike earlier AI solutions, ChatGPT features excellent conversational and creative reasoning capabilities across multiple domains. There have been empirical studies demonstrating that ChatGPT can act as a designer, user, or product, efficiently performing the tasks assigned to it and providing most appropriate responses[2]. However, we still know very little about the design ideation process and its performance in terms of productivity.

No metrics found for this document.
Contact IEEE to Subscribe

References

References is not available for this document.