Working with Young-Ho Kim at Naver AI, I built an interface that helps users to generate evidence-baesd exercise plans using an LLM chatbot.

This work was done during my internship at Naver AI. (under review)

Keyscreen of our system

[My role in this project]
Leading the project

Advised by Lucy Lu Wang and Gary Hsieh, I built a system that automatically generates design cards from HCI papers using generative AI models, such as GPT-3 and DALL-E 2. (CHI 2024, to appear)

Pipeline of generating design cards using our system

[My role in this project]
Leading the project

Working with Ruican Zhong, Gary Hsieh, Lucas Colusso, and Kaiser Permanente research team, we built an LLM-infused Miro plugin that helps designers to generate causal pathway diagrams (CPDs) to inform their theory-driven designing. (CHI 2024, to appear)

An example of causal pathway diagram (CPD)

[My role in this project]
Building a system

Working with Taewan Kim and Hwajung Hong, we explored the design space of generative language models (e.g., GPT-3) in supporting a reflective writing process. (CHI 2024, to appear)

Keyscreen of our system

[My role in this project]
System development, design ideation

Advised by Gary Hsieh, we built a chatbot that helps familiarization of ad hoc teammates. Plus, we revealed the efficacy of such familiarization in ad hoc team performance. (CHI '23 paper)

Keyscreen of our system

[My role in this project]
Leading the project

In this project, we investigated how older adults use online videos for learning. To better understand the online learning of older adults, we adopted a mixed-method approach: (1) analyzing 41.8M logs extracted from K-MOOC, a Korean MOOC (Massive Open Online Course) platform and (2) running in-depth interview sessions with older adults.

Led by Seoyoung Kim, this project was advised by Juho Kim. (CHI '23 paper)

Example of the data analysis from our study

[My role in this project]
Running interview sessions, taking part in thematic analysis, analyzing log data, writing

To guide the design of explanation for assessing damages from satellite imageries, we are working on characterizing how humans generate explainability. I'm excited to learn about generating model explainability from my wonderful colleagues.

Working with Katelyn Morrison, this project was co-advised by Ken Holstein and Adam Perer. This work was accepted at CSCW 2023 and NeurIPS '21 Workshop (AI for Humanitarian Assistance and Disaster Response).

Examples of the explanation in damage detection tasks from satellite imageries

[My role in this project]
User study, open-coding responses, system development

In this project, we are investigating methods to assist emotional support processes in online mental health community, particularly by leveraging AI.

Specifically, to support their community interactions, we developed and deployed (i) multi-class sentiment detection model using BERT to support the affectionate feedback process and (ii) keyword extraction based on the saliency of each keywords to facilitate the experience-sharing processes.

Co-advised by Hwajung Hong and Jinwook Seo, this work was published in CHI 2022 Extended Abstracts (Late-Breaking Work) and CHI 2022 Workshop (Future of Emotion in HCI).

Keyscreens of our system

[My role in this project]
Leading the project, preliminary interview, storyboarding, writing, system development

Often referred to as a 'war', course registration process of Seoul National University is highly competitive as it is first come, first served.

In this process, students sometimes accidentally reload the website, where the system immediately returns error message and forces user to log-in again. (I suspect this is to prvent users from using macro, but no one knows..) This is disastrous, since logging in makes users waste their times a lot in such a urgent situation.

To address this, I made a browser extension, where users can simply click one button to escape from the error message. This tweak is supported on both Chrome and Whale browser.

Keyscreen of SNU CRS Refresher

[My role in this project]
Independent project

Have you ever wished a robot to send romantic messages to the other on behalf of yourself? Having a conversation in a romantic relationship is often difficult. Sometimes we ask our friends for help, but such help is limited.

In this project, we assumed that an AI agent in chat settings became so smart that it perfectly analyzes the counterpart's emotion and suggests responses in a chat setting. Along with a prototype app LOVEGORITHM that helps such a romantic relationship, we designed and developed an LOVEGORITHM online user community that illustrates possible feedback and behaviors of users. Check out the link above!

This work was submitted as a team project assignment to the Spring 2021 Creative Research Practice course.

Keyscreens of LOVEGORITHM

Keyscreen of LOVEGORITHM online user community

[My role in this project]
Web development, prototype design, setting up dialogues, ideation

We aimed to develop a system that facilitates users' conversation on political issues and developed a high-fidelity prototype: PoliNewsBot.

This work was submitted as a team project assignment to the Spring 2021 HCI Theory and Practice course.

Keyscreens of PoliNewsBot

[My role in this project]
System development, ideation, setting up dialogues

We explored the role and behavior of entities surrounding translation algorithms, in a situation where users trick and game them.

This work was publised in CSCW 2021.

Entities of reviewing communities where translation algorithm is applied

[My role in this project]
Writing, designing figures

Due to the irreversible characteristics and disastrous effects of Age-related Macular Degeneration (AMD), a precise diagnosis of the symptoms is extremely important. Yet, paper-based Amsler Grid, the most prevalent testing method, is highly limited in that it requires the indirect report of patients and quantitative reporting is difficult.

In this project, I designed and developed a touch-based Amsler grid web app. As such, I aimed to support patients' exact report of their regions of symptoms.

What made this project special to me is that, I made a LaTeX template for writing this paper! I found that my friends preparing for their thesis always felt it difficult to produce a thesis format, since our department only gave us a 'scanned' version of template, not a real document. Thus, I generated a template which can be found here (this template was built upon previous Ph.D. dissertation template under license)

This study was conducted for my B.S. thesis, and later published in HCI Korea 2022.

Keyscreen of AmslerTouch

[My role in this project]
Independent project

Prolonged time of computer use increased the prevalence of ocular problems including eyestrain, tired eyes, irritation, redness, blurred vision, and double vision, collectively referred to as computer vision syndrome. In this study, we aim to explore the interface elements of computer-based intervention for computer vision syndrome to set design guidelines based on pros/cons of each interface element.

In this project, I developed LiquidEye: an intervention application targeted to MacOS. In order to understand which design elements of intervention app do users prefer, we made the system to collect each user's time-series system preferences. We later jointly analyzed them with the self-reported satisfaction in order to identify the significance of each element statistically.

This work was published in Journal of Medical Internet Research.

Keyscreen of LiquidEye

[My role in this project]
System development, running interview sessions, writing

It is a prevalent behavior of having a chat with strangers in online settings where people can easily gather. Yet, people often find it difficult to initiate and maintain conversation due to the lack of information about strangers.

Hence, we aimed to facilitate conversation between the strangers with the use of machine learning (ML) algorithms and present BlahBlahBot, an ML-infused chatbot that moderates conversation between strangers with personalized topics. Based on social media posts, BlahBlahBot supports the conversation by suggesting topics that are likely to be of mutual interest between users.

A user study with three groups (control, random topic chatbot, and BlahBlahBot; N=18) found the feasibility of BlahBlahBot in increasing both conversation quality and closeness to the partner, along with the factors that led to such increases from the user interview. Overall, our preliminary results imply that an ML-infused conversational agent can be effective for augmenting a dyadic conversation.

This work was published in CHI 2021 Extended Abstracts (Late-Breaking Work).

Framework of BlahBlahBot

[My role in this project]
System development, running interview sessions, writing

According to a recent survey conducted by American Psychological Association [1], academic stress is cited as the number one stressor in students' daily life. This issue is specifically considered serious in South Korea, where half of Korean teenagers experienced a thought of suicidal and academic stress is reported as a top-ranked attribute to such phenomenon [2].

This, however, cannot be solely dealt with reducing academic affair. Since such academic phenomenon is multi-faceted with lots of stakeholders involved (e.g., homeroom teacher, parents, and friends), we should not naïvely understand the issue. For example, high schools often focus on increasing the number of students entering so-called 'prestigious universities.' However, by solely focusing on the name of university rather than a major, this often undermines the agency of students' decision on their future career, and leading students to suffer from subsidious academic stresses as well as a stress on the study itself.

Since the academic curriculum drastically changes over time and policy-makers and relatively older people cannot easily understand such a situation, we aimed to show how difficult it is for high school students to 'survive' under such factors that often lead to academic stresses. By having users choose a choice in each crossroad of choices and differentiating the following storieline, we, though indirectly, let them feel how stressed high school students would be in the midst of a choice.

Keyscreens of Easier said than done

REFERENCE
[1] American Psychological Association. (2014). Stress in America: Are teens adopting adults’ stress habits. Washington, DC: Author.
[2] Kang, Y. (2014). Poll shows half of Korean teenagers have suicidal thoughts. The Wall Street Journal.

[My role in this project]
System development

In this project, we designed an application for supporting those who study abroad, but came back due to COVID-19. Since they often suffer from lack of sleep due to the time difference, we aimed to support them with managing their health, at the same time not undermining their classworks. In order to precisely understand their needs, we conducted extensive user interview sessions, YouTube v-logger observation study, diary study, and web survey.

As a result, we designed '夜-planet', an application that supports students under such circumstances. '夜' is a Chinese character for 'night', and '夜-planet' stands for 'nocturnal.'

If you are interested in taking a look at our prototype, please check out the link above:) (Korean)

Prototype of 夜-planet

[My role in this project]
User study, ideating design elements

At the end of my sophomore year, I read one CHI paper by chance: 'Blocks4All: overcoming accessibility barriers to blocks programming for children with visual impairments.' Written by Milne and her colleagues, this paper explores the methods of overcoming accessibility issues in existing block-based programming tools. I was super intrigued by how HCI researchers try to understand user groups and reflect design implications into an artifact.

Surprisingly, at that moment my supervisor asked if I'm willing to lead a project for developing an AAC (Augmentative and Alternative Communication) application. Definitely I said yes, because I found it really difficult to take part in any research project as an undergrad without any previous research experience then. From then, I spent almost every night developing an iOS app, while simultaneously conducting user studies, reading relevant papers, and even designing! Literally everything was new: from being funded for a research to getting an approval from IRB for the evaluation! Fortunately, at the moment when I finished my research, we were almost at the deadline of CHI 2020 and submitted our work there, and got accepted with an Honorable Mention Award.

To summarize our paper briefly, we tried not to restrict a stakeholder of AAC to only a child, but also viewed their caregivers very important in the process of child's communication. Based on this research context, we aimed to develop a system that helps them collaborate to drive the best strategies on child's communication. As a result, we developed Talkingboogie, a mobile AAC system for children with developmental disabilities.

Usage flow of TalkingBoogie system

TalkingBoogie system consists of two mobile apps: TalkingBoogie-AAC for caregiver-child communication, and TalkingBoogie-Coach supporting caregiver collaboration.

Keyscreens of TalkingBoogie-AAC

Keyscreens of TalkingBoogie-Coach

[My role in this project]
System development, writing, user study, running interview sessions, data analysis

I believe that one's favourite set of music in a specific period represents own emotion at that period. To prove this, I listed all my favourite songs by each semester. Then, I analyzed the emotion of each song using Cyanite, and I visualized the results with D3.js.

Well, I was super shocked by the result. For my depressing time, I used to listen to melancholic songs. For my highest period, my playlist was full of happy and energetic songs. Why don't you try with your own playlist?

This design work was submitted as an assignment to Spring 2020 Design Thinking for Communication course.

[My role in this project]
Independent project

I personally don't prefer to believe things that haven't been proved yet. But some posts in social networking services make people believe fake or unproven news to be correct, and some even try to convey these for their political purposes.

In this project, I aimed to provide examples of some 'controversial' information that emerged during the COVID-19 situation. Then, I tried to let readers decide on it. Well, this project was tough because COVID-19 was a 'relatively new' phenomenon then, and it lacked scientifically proven information. However, I'm pretty fascinated with how 'seemingly ridiculous' information is spread throughout people and later considered to be true.

This design work was submitted as an assignment to Spring 2020 Design Thinking for Communication course.

[My role in this project]
Independent project

It's always fun to imagine things that won't happen XD

In this project, I assumed that well-known tech companies run their own football team in a 'Tech Champions League.' In this tournament, each team competes using own market cap. For this project, I mainly focused on designing small multiples with the following question: What comes to mind immediately when I think of the company?

This design work was submitted as an assignment to Spring 2020 Design Thinking for Communication course.

[My role in this project]
Independent project

In this collaborative project among Samsung Research, SNU HCI+d Lab, and Yonsei university, we aimed to design a coherent visual identity for Bixby: a smart agent deployed to Samsung appliances.

During the study, I took part in developing prototypes and conducting user experiment.

Example screen we used during the user study

[My role in this project]
Prototype development, running experiment, writing

I've been working as an iOS developer in a local micro-mobility sharing startup for about 2 years. As working in a tech company, I got to know that understanding possible users is extremely important for the success of service and business.

Thus, I decided to take 'Digital Ethnography' class, where students choose one topic they want to deal with and explore user groups to better understand the topic. With the topic of understanding why users hesitate riding a sharing mobility device and discuss solutions using ethnography, I ran a couple of observation and interview studies with college students (N=6).

Even though I could run the user observation study neither for a long term nor with a large number (COVID-19), it was really interesting to understand how HCI researchers explore users with qualitative methodologies in the real-world context.

Please kindly understand that the paper was written in Korean language.

[My role in this project]
Independent project

Although text-based conversational agents (chatbots) have a great potential of journaling diets and managing one's health, it is suffering from the low acceptance of users. To overcome this, we proposed an idea of applying the persona of real world caregivers into the chatbot.

Led by Youjin Hwang, we conducted a series of studies regarding this topic. Specifically, in this study, we aimed to identify several important linguistic features that make users perceive a chatbot as a real person.

This study was published in MobileHCI 2020 Extended Abstracts (Late-Breaking Result).

[My role in this project]
Writing

Although text-based conversational agents (chatbots) have a great potential of journaling diets and managing one's health, it is suffering from the low acceptance of users. To overcome this, we proposed an idea of applying the persona of real world caregivers into the chatbot.

Led by Youjin Hwang, we conducted a series of studies regarding this topic. Specifically, in this study, we aimed to compare user perception on personas (doctor, family member, and w/o persona) applied to a chatbot. Although this work is done with Wizard-of-Oz methodology, we expect that the findings would be extensible to automated cases with ML.

This study was presented in CHI 2020 Workshop (Conversational Agents for Health and Wellbeing).

Three personas applied to a chatbot

[My role in this project]
System development, running experiment, writing

Juvis is a Korean diet-managing company. In order to give enough information and lead users to successfully book a reservation, we designed a chatbot. This experience led me to learn how we might design a chatbot, and this motivated me to design a chatbot in my another project on applying the persona on a chatbot.

Keyscreens of Juvis chatbot

[My role in this project]
System development

For more than 2 years, I've been working as an iOS developer in Elecle, a Korean electric mobility-sharing startup.

Since every single step of renting a mobility device and returing it is done in a mobile app, mobile app development is considered extremely crucial in mobility sharing services. Thus, we have put much emphasis on increasing usability and usefulness of the mobile app for end-users and devised various interaction methods within our app.

Elecle is currently available in more than 5 cities in Korea, including Seoul, Suwon, Bucheon, Gimpo, and Sejong.

Me with an Elecle bike XD

Keyscreens of Elecle iOS app

[My role in this project]
System development, design ideation

It was extremely difficult for me to keep track of the courses I've taken during the undergraduate study. I'm surprised that many other friends also fased similar problem.

To make this process hassle-free, I made an iOS app called ECE grad. Using this application, undergrads in ECE department may easily track their previously taken courses. Plus, this also shows how many credits they should additionally take. Plus, this system automatically visualizes the history and show some cheer-up messages for inducing students to take courses and keep track of their course history.

However, some of my friends suggested that it was a bit time-consuming to manually add courses into the system. Based on this feedback, in order to facilitate the process of entering their previous courses, I added a crawling function that automatically crawls the relevant data within SNU mypage, by simply entering their ID and password.

Keyscreens of ECE grad

[My role in this project]
Independent project

As I started my internship at HCI+d lab, I found that the website was a bit outdated. Thus, I worked with my colleagues to design the website (based upon the previously designed template) and added up the lab members' profile.

It was a great experience to contribute to the lab with my skillsets!

My profiile here :)

[My role in this project]
Development, design