Dr. Joongi Shin
Hi, I'm a Postdoctoral researcher at Aalto University, supervised by prof. Antti Oulasvirta (User Interface Group) and prof. Andrés Lucero. I received my Ph.D. in Industrial Design from Korea Advanced Institute of Science and Technology (KAIST) in 2021. I investigate integrating AI in creative activities among human collaborators.
Research focus: HCI, reinforcement learning, conversational agents, collaborative ideation, co-design.
Previous studies: Robotic furniture, posture manipulation, collaboration, design tools for users, VR/AR.
News
2022 Dec: My first workshop as a postdoc is accepted at CHI '23.
2022 Oct: I gave a presentation in person at UIST '22.
2022 Sep: I received a postdoctoral research fellowship from National Research Foundation of Korea (NRF).
2022 Aug: My first paper as a postdoc is accepted at UIST '22 :)
2021 Sep: Now I am a postdoc researcher at Antti Oulasvirta's and Andrés Lucero's group at Aalto University.
2021 Aug: I received a Ph.D. degree in Industrial Design from KAIST.
2017 Aug: I started the joint MA and Ph.D. program at KAIST.
2016 Aug: I joined the myDesign lab at KAIST as a MA student.
Ongoing project
AI facilitators for human-human collaborative ideation
How can AI support collaborative ideation among people? The advancement in AI has enabled creative activities between humans and AI. Building on people's creations, AI can effectively diversify designs, generate alternatives, and even provide experts' knowledge in people's ideation process. As an interactive agent, AI has evolved from a creative tool to an ideation 'partner' and to a 'facilitatior'.
Consensus-building is an essential process for the success of co-design projects. To build consensus, stakeholders need to discuss conflicting needs and viewpoints, converge their ideas toward shared interests, and grow their willingness to commit to group decisions. However, managing group discussions is challenging in large co-design projects with multiple stakeholders. In this paper, we investigate the interaction design of a chatbot that can mediate consensus-building conversationally. By interacting with individual stakeholders, the chatbot collects ideas to satisfy conflicting needs and engages stakeholders to consider others’ viewpoints, without having stakeholders directly interact with each other. Results from an empirical study in an educational setting (N = 12) suggest that the approach can increase stakeholders’ commitment to group decisions and maintain the effect even on the group decisions that conflict with personal interests. We conclude that chatbots can facilitate consensus-building in small-to-medium-sized projects, but more work is needed to scale up to larger projects.