Joongi Shin

Dr. Joongi Shin

** Looking for faculty position **

I'm a Postdoctoral researcher at Aalto University, supervised by Prof. Antti Oulasvirta (Computational Behavior Lab) 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 how to best use emerging technologies and AI to support human creative and design activities.

Primary Research Keywords: HCI, user-centered design, collaborative creativity, generative AI
Secondary Research Keywords: unobtrusive interaction, robotic furniture, posture manipulation, design tools, VR/AR.

Research Vision

My career objective is to make a breakthrough in human creativity — improving how creative experts perform their creativity in deriving more novel and useful outcomes. I aim to achieve this by integrating artificial intelligence (AI) into creative activities. I believe that AI bears great promise in assisting creative activities such as problem-solving and design. However, much of AI’s potential remains untapped because we fail to understand the nature of creative practice itself. A well-known example is the consequence of using generative AI (GenAI) as a source of inspiration. While individuals can increase their idea quality by building on AI-generated outcomes, they tend to converge on similar ideas as GenAI lacks competence in generating original concepts. Another negative consequence is that utilizing GenAI shifts individuals’ creative efforts toward merely formulating better instructions for GenAI or evaluating alternatives created using GenAI. This can cause a critical problem, unobtrusively limiting people’s creative capacity for generating innovative solutions for society.

I want to solve this dilemma of human-AI creativity — while using AI helps increase outcome quality, it degrades individuals’ creative competence over time. This calls for a deep understanding of the mechanisms behind human creativity and empirical testing of interactive systems that can help creative practitioners make the most of AI. Accordingly, my overarching research questions are (a) how using AI in design activities influences designers and (b) how to design human-AI interactions that benefit designers.

News

2024 Nov: Attending OzCHI'24 to present our work on Facilitating Asynchronous Idea Generation and Selection with Chatbots (project page TBA)
2024 July: Invited to AI and I Hackathon as a keynote speaker about how generative AI can improve human creativity and jury.
2024 July: Attending DIS'24 to present our work on human-AI workflows for generating personas (project page).
2023 Oct: Invited as a guest speaker by Prof. Seungwoo Je at Southern University of Science and Technology, China.
2023 Jun: Visiting Prof. Peter Dalsgaard at Aarhus University, Denmark.
2023 Apr: Attending CHI'23 to hold a workshop about integrating AI in human-human collaboration (workshop page).

2022 Oct: Attending UIST'22 to present our work on chatbot facilitators for conflict resolution (project page).
2022 Sep: Received a postdoctoral research fellowship from the National Research Foundation of Korea (NRF).
2022 Aug: Published the first paper as a postdoc in UIST '22 :)
2021 Sep: Starting as a postdoctoral researcher at Prof.Antti Oulasvirta's and Prof.Andrés Lucero's group at Aalto University.
2021 Aug: Received a Ph.D. degree in Industrial Design from KAIST.
- : Studying design tools for human collaborators and unobtrusive interaction with robotic furniture.
2017 Aug: Starting the combined MA and Ph.D. program at the Industrial Design department from KAIST.
2016 Aug: Joined the myDesign lab at KAIST as a MA student.

Selected Publications

Understanding Human–AI Workflows for Generating Personas

Joongi Shin, Michael A. Hedderich, Bartłomiej Jakub Rey, Andrés Lucero, Antti Oulasvirta

Proceedings of the 2024 ACM Designing Interactive Systems Conference

[DOI] [PAPER] [Project]

One barrier to deeper adoption of user-research methods is the amount of labor required to create high-quality representations of collected data. Trained user researchers need to analyze datasets and produce informative summaries pertaining to the original data. While Large Language Models (LLMs) could assist in generating summaries, they are known to hallucinate and produce biased responses. In this paper, we study human--AI workflows that differently delegate subtasks in user research between human experts and LLMs. Studying persona generation as our case, we found that LLMs are not good at capturing key characteristics of user data on their own. Better results are achieved when we leverage human skill in grouping user data by their key characteristics and exploit LLMs for summarizing pre-grouped data into personas. Personas generated via this collaborative approach can be more representative and empathy-evoking than ones generated by human experts or LLMs alone. We also found that LLMs could mimic generated personas and enable interaction with personas, thereby helping user researchers empathize with them. We conclude that LLMs, by facilitating the analysis of user data, may promote widespread application of qualitative methods in user research.

Chatbots Facilitating Consensus-Building in Asynchronous Co-Design

Joongi Shin, Michael A. Hedderich, Andrés Lucero, Antti Oulasvirta

UIST '22 I4th Annual ACM Symposium on User Interface Software and Technology

[DOI] [PAPER]

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.

Slow Robots for Unobtrusive Posture Correction

Joongi Shin, Eiji Onchi, Maria Jose Reyes, Junbong Song, Uichin Lee, Seung-Hee Lee, Daniel Saakes

CHI '19: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

[DOI]

Prolonged static and unbalanced sitting postures during computer usage contribute to musculoskeletal discomfort. In this paper, we investigated the use of a very slow moving monitor for unobtrusive posture correction. In a first study, we identified display velocities below the perception threshold and observed how users (without being aware) responded by gradually following the monitor's motion. From the result, we designed a robotic monitor that moves imperceptible to counterbalance unbalanced sitting postures and induces posture correction. In an evaluation study (n=12), we had participants work for four hours without and with our prototype (8 in total). Results showed that actuation increased the frequency of non-disruptive swift posture corrections and significantly reduced the duration of unbalanced sitting. Most users appreciated the monitor correcting their posture and reported less physical fatigue. With slow robots, we make the first step toward using actuated objects for unobtrusive behavioral changes.

Page updated

Google Sites

Report abuse