Coherent visual design through attribute-specific feedback: a hybrid approach to intelligent design agents

ABSTRACT

The scope of visual design is expanding to promote products and services across digital communication platforms, but support for coherent design with style guides seems limited. Based on the literature on style, coherence and design support tools with different levels of intelligence, we describe coherence in visual design and propose to integrate preset style guidelines and constraints into feedback interactions to support achieving visual coherence. After formative research with expert designers, we prototype a pseudo-AI design support tool to simulate attribute-specific feedback and conduct user research to probe how participants engage with feedback provided by a human wizard acting as an intelligent agent. We analyze patterns of feedback and types of reactions observed in participants’ design processes and outcomes. We then discuss the implications of attribute-specific feedback to describe visual coherence as a meta-property of design, and intelligent agents that guide situational judgements about visual coherence through feedback interactions.

KEYWORDS:

• Visual design
• style attributes
• visual coherence
• feedback
• intelligent agents

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Seoyeon Jang

Seoyeon Jang took a M.S. degree in Industrial Design at Korea Advanced Institute of Science and Technology (KAIST). She graduated from the Sungkyunkwan University with a Bachelor’s Degree in Bio-Mechatronics and Visual Communication Design. She is passionate about designing communications with visual cues or conceptual interaction between people through electronic devices.

Yunwoo Jeong

Yunwoo Jeong is a Ph.D. Candidate in the industrial design department at Korea Advanced Institute of Science and Technology (KAIST). He received B.Sc and M.Sc industrial design from KAIST. He is interested in the development of an augmented reality environment for iterative and computational prototyping process of an interactive kinetic artefact.

Heekyoung Jung

Heekyoung Jung is an Associate Professor of Communication Design in the School of Design at University of Cincinnati. She earned her B.S. and M.S. in Industrial Design from KAIST and her Ph.D. in Human–Computer Interaction Design from Indiana University Bloomington. She specializes in user interface and experience design of information and product systems; conducts practice-based, reflective, and exploratory design studies to understand and augment human creativity with emerging technologies.

Tek-Jin Nam

Tek-Jin Nam is a professor and the director of Co.Design:Interaction Design Research(CIDR) Lab at KAIST, Korea. He received a B.S. and a M.S. in Industrial Design from KAIST, and a PhD in Design from Brunel University. He is the deputy editor-in-chief of Archives of Design Research journal, the Secretary General of IASDR(International Association of Societies of Design Research), and an International Advisory Committee Member of DRS(Design Research Society). His research interests lie at design-oriented human–computer interaction, focusing on creating people centric values of future products and services and systematic approaches to creative design and innovation. He is also interested in practice-led, practice-oriented design research.