THE COGNITIVE STUDY OF DESIGN IDEATION IN AN AI-BASED CO-CREATIVE SKETCHING PARTNER

Doctoral Candidate Name: 
Jingoog Kim
Program: 
Computing and Information Systems
Abstract: 

The primary goal of design is to provide effective and innovative solutions for solving design problems. Ideation, an initial idea generation for conceptualizing a design solution, is a key step that can lead design to an innovative design solution in the design process. Idea generation is a process that allows designers to explore many different areas of the design solution space. Due to the importance of ideation, many studies focused on understanding the cognitive processes in idea generation and evaluating ideation. This thesis focuses on the idea generation process based on conceptual similarity in a human-AI collaboration. Co-creative systems in design allow users to collaborate with an AI agent on open-ended creative tasks in the design process. Co-creative systems share the characteristics of both creativity support tools helping users achieve creative goals and algorithms that generate creative content autonomously. Co-creative systems support design creativity by encouraging the exploration of design solutions in the initial idea generation. However, there is a lack of studies about the effect of co-creative systems on the cognitive process during ideation. This thesis posits that the contribution of an AI partner in design is associated with specific properties of ideation such as novelty, variety, quality, and quantity of ideas.
This thesis presents a co-creative system that enhances design creativity in the initial idea generation process. The Collaborative Ideation Partner (CIP) is a co-creative design system that selects and presents inspirational images based on their conceptual similarity to the design task while the designer is sketching. This thesis addresses how the conceptual similarity of the contribution of the AI partner influences design ideation in a co-creative system. This thesis presents an experiment with a control condition in which the images are selected randomly from a curated database for inspiration and a treatment condition in which conceptual similarity is the basis for selecting the next inspiring image. To evaluate the ideation during the use of CIP, this thesis employed an aggregate analysis and a temporal analysis. The findings show that the AI model of conceptual similarity used in the treatment condition has a significant effect on the novelty, variety, and quantity of ideas during human design ideation.

Defense Date and Time: 
Wednesday, December 15, 2021 - 10:30am
Defense Location: 
Zoom: https://uncc.zoom.us/j/97202961990
Committee Chair's Name: 
Mary Lou Maher
Committee Members: 
Dr. John Gero, Dr. Doug Markant, Dr. Gabriel Terejanu