Taewook Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Taewook Kim has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Hyomin Han
Learning Sciences, Northwestern University, United States
2 shared publications - John Joon Young Chung
Midjourney, San Francisco, California, USA
2 shared publications - Matthew Kay
Northwestern University, USA
2 shared publications - Qingyu Guo
The Hong Kong University of Science and Technology
2 shared publications - Alex Calderwood
Computational Media, University of California, Santa Cruz, USA
1 shared publication - Angela Christine Roberts
Department of Computer Science, Western University, London, Ontario, Canada
1 shared publication
Latest Publications
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-28
Steering AI-driven Personalization of Scientific Text for General Audiences
Digital media platforms (e.g., science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy levels, and personal backgrounds, making effective science communication challenging. To address this challenge, we designed TranSlider, an AI-powered tool that generates personalized translations of scientific text based on individual user profiles (e.g., hobbies, location, and education). Our tool features an interactive slider that allows users to steer the degree of personalization from 0 (weakly relatable) to 100 (strongly relatable), leveraging LLMs to generate the translations with chosen degrees. Through an exploratory study with 15 participants, we investigated both the utility of these AI-personalized translations and how interactive reading features influenced users' understanding and reading experiences. We found that participants who preferred higher degrees of personalization appreciated the relatable and contextual translations, while those who preferred lower degrees valued concise translations with subtle contextualization. Furthermore, participants reported the compounding effect of multiple translations on their understanding of scientific content. Drawing on these findings, we discuss several implications for facilitating science communication and designing steerable interfaces to support human-AI alignment.
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-28
Open AccessSteering AI-driven Personalization of Scientific Text for General Audiences
Digital media platforms (e.g., science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy levels, and personal backgrounds, making effective science communication challenging. To address this challenge, we designed TranSlider, an AI-powered tool that generates personalized translations of scientific text based on individual user profiles (e.g., hobbies, location, and education). Our tool features an interactive slider that allows users to steer the degree of personalization from 0 (weakly relatable) to 100 (strongly relatable), leveraging LLMs to generate the translations with chosen degrees. Through an exploratory study with 15 participants, we investigated both the utility of these AI-personalized translations and how interactive reading features influenced users' understanding and reading experiences. We found that participants who preferred higher degrees of personalization appreciated the relatable and contextual translations, while those who preferred lower degrees valued concise translations with subtle contextualization. Furthermore, participants reported the compounding effect of multiple translations on their understanding of scientific content. Drawing on these findings, we discuss several implications for facilitating science communication and designing steerable interfaces to support human-AI alignment.
- Open Access
- 5 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 236-241
Supporting Material Writing Practice with Phraselette, a Palette of Phrases
- 5 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 236-241
Open AccessSupporting Material Writing Practice with Phraselette, a Palette of Phrases
- Open Access
- 2 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (2) , 1-35
MentalImager: Exploring Generative Images for Assisting Support-Seekers' Self-Disclosure in Online Mental Health Communities
Support-seekers' self-disclosure of their suffering experiences, thoughts, and feelings in the post can help them get needed peer support in online mental health communities (OMHCs). However, such mental health self-disclosure could be challenging. Images can facilitate the manifestation of relevant experiences and feelings in the text; yet, relevant images are not always available. In this paper, we present a technical prototype named MentalImager and validate in a human evaluation study that it can generate topical- and emotional-relevant images based on the seekers' drafted posts or specified keywords. Two user studies demonstrate that MentalImager not only improves seekers' satisfaction with their self-disclosure in their posts but also invokes support-providers' empathy for the seekers and willingness to offer help. Such improvements are credited to the generated images, which help seekers express their emotions and inspire them to add more details about their experiences and feelings. We report concerns on MentalImager and discuss insights for supporting self-disclosure in OMHCs.
- 2 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (2) , 1-35
Open AccessMentalImager: Exploring Generative Images for Assisting Support-Seekers' Self-Disclosure in Online Mental Health Communities
Support-seekers' self-disclosure of their suffering experiences, thoughts, and feelings in the post can help them get needed peer support in online mental health communities (OMHCs). However, such mental health self-disclosure could be challenging. Images can facilitate the manifestation of relevant experiences and feelings in the text; yet, relevant images are not always available. In this paper, we present a technical prototype named MentalImager and validate in a human evaluation study that it can generate topical- and emotional-relevant images based on the seekers' drafted posts or specified keywords. Two user studies demonstrate that MentalImager not only improves seekers' satisfaction with their self-disclosure in their posts but also invokes support-providers' empathy for the seekers and willingness to offer help. Such improvements are credited to the generated images, which help seekers express their emotions and inspire them to add more details about their experiences and feelings. We report concerns on MentalImager and discuss insights for supporting self-disclosure in OMHCs.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts
Generative AI has the potential to create a new form of interactive media: AI-bridged creative language arts (CLA), which bridge the author and audience by personalizing the author’s vision to the audience’s context and taste at scale. However, it is unclear what the authors’ values and attitudes would be regarding AI-bridged CLA. To identify these values and attitudes, we conducted an interview study with 18 authors across eight genres (e.g., poetry, comics) by presenting speculative but realistic AI-bridged CLA scenarios. We identified three benefits derived from the dynamics between author, artifact, and audience: those that 1) authors get from the process, 2) audiences get from the artifact, and 3) authors get from the audience. We found how AI-bridged CLA would either promote or reduce these benefits, along with authors’ concerns. We hope our investigation hints at how AI can provide intriguing experiences to CLA audiences while promoting authors’ values.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Top Cited PapersOpen AccessAuthors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts
Generative AI has the potential to create a new form of interactive media: AI-bridged creative language arts (CLA), which bridge the author and audience by personalizing the author’s vision to the audience’s context and taste at scale. However, it is unclear what the authors’ values and attitudes would be regarding AI-bridged CLA. To identify these values and attitudes, we conducted an interview study with 18 authors across eight genres (e.g., poetry, comics) by presenting speculative but realistic AI-bridged CLA scenarios. We identified three benefits derived from the dynamics between author, artifact, and audience: those that 1) authors get from the process, 2) audiences get from the artifact, and 3) authors get from the audience. We found how AI-bridged CLA would either promote or reduce these benefits, along with authors’ concerns. We hope our investigation hints at how AI can provide intriguing experiences to CLA audiences while promoting authors’ values.
- Open Access
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-26
Opportunities in Mental Health Support for Informal Dementia Caregivers Suffering from Verbal Agitation
People with dementia (PwD) often present verbal agitation such as cursing, screaming, and persistently complaining. Verbal agitation can impose mental distress on informal caregivers (e.g., family, friends), which may cause severe mental illnesses, such as depression and anxiety disorders. To improve informal caregivers' mental health, we explore design opportunities by interviewing 11 informal caregivers suffering from verbal agitation of PwD. In particular, we first characterize how the predictability of verbal agitation impacts informal caregivers' mental health and how caregivers' coping strategies vary before, during, and after verbal agitation. Based on our findings, we propose design opportunities to improve the mental health of informal caregivers suffering from verbal agitation: distracting PwD (in-situ support; before), prompting just-in-time maneuvers (information support; during), and comfort and education (social & information support; after). We discuss our reflections on cultural disparities between participants. Our work envisions a broader design space for supporting informal caregivers' well-being and describes when and how that support could be provided.
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-26
Open AccessOpportunities in Mental Health Support for Informal Dementia Caregivers Suffering from Verbal Agitation
People with dementia (PwD) often present verbal agitation such as cursing, screaming, and persistently complaining. Verbal agitation can impose mental distress on informal caregivers (e.g., family, friends), which may cause severe mental illnesses, such as depression and anxiety disorders. To improve informal caregivers' mental health, we explore design opportunities by interviewing 11 informal caregivers suffering from verbal agitation of PwD. In particular, we first characterize how the predictability of verbal agitation impacts informal caregivers' mental health and how caregivers' coping strategies vary before, during, and after verbal agitation. Based on our findings, we propose design opportunities to improve the mental health of informal caregivers suffering from verbal agitation: distracting PwD (in-situ support; before), prompting just-in-time maneuvers (information support; during), and comfort and education (social & information support; after). We discuss our reflections on cultural disparities between participants. Our work envisions a broader design space for supporting informal caregivers' well-being and describes when and how that support could be provided.
- Open Access
- 8 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 36-38
Opportunities to Support Communal Experiences of Deaf and Hard-of-Hearing People in Live Popular Music Concerts
Deaf and hard-of-hearing (D/HH) people attend live popular music concerts. While communal experiences such as fan chanting and group dancing are often the major reasons for going to concerts, no existing tools have been designed to support such experiences for D/HH people in live popular music concerts. We interviewed five D/HH people to understand current challenges and technological demands for better communal experiences in live popular music concerts. All participants expressed eagerness to participate in communal activities. They could follow behavioral group activities that were visually recognizable (e.g., audience waves). However, due to the lack of other sensory guides, they reported that they had experienced difficulties joining sound-based communal activities (e.g., fan chanting). To tackle these challenges, our participants suggested utilizing visual stimuli, such as AR glasses, to provide some contextual information that enables D/HH people to understand and pinpoint the right moment to engage in communal experiences.
- 8 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 36-38
Open AccessOpportunities to Support Communal Experiences of Deaf and Hard-of-Hearing People in Live Popular Music Concerts
Deaf and hard-of-hearing (D/HH) people attend live popular music concerts. While communal experiences such as fan chanting and group dancing are often the major reasons for going to concerts, no existing tools have been designed to support such experiences for D/HH people in live popular music concerts. We interviewed five D/HH people to understand current challenges and technological demands for better communal experiences in live popular music concerts. All participants expressed eagerness to participate in communal activities. They could follow behavioral group activities that were visually recognizable (e.g., audience waves). However, due to the lack of other sensory guides, they reported that they had experienced difficulties joining sound-based communal activities (e.g., fan chanting). To tackle these challenges, our participants suggested utilizing visual stimuli, such as AR glasses, to provide some contextual information that enables D/HH people to understand and pinpoint the right moment to engage in communal experiences.
- Open Access
- 8 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 3-7
Facilitating Continuous Text Messaging in Online Romantic Encounters by Expanded Keywords Enumeration
An increasing number of people are looking for romantic partners online. Many of them first converse online before deciding whether or not to meet in-person. However, it is often challenging to have smooth and continuous conversations online with someone who they have never met in person. To handle this problem, we built a proof-of-concept system, Tomi, that dynamically suggests various conversation topic seeds related to the latest received messages in real-time. It selects a keyword from an incoming message and returns five contextually relevant topic seeds. In a qualitative study with eight dyads that simulated the common setting of online match-making, users could continue their conversations either by directly or indirectly utilizing the suggested topic seeds. Also, our system boosted their confidence during the chat. Lastly, we analyzed the trade-offs between several design alternatives and presented our reflections on a system supporting continuous conversations with diverse topics.
- 8 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 3-7
Open AccessFacilitating Continuous Text Messaging in Online Romantic Encounters by Expanded Keywords Enumeration
An increasing number of people are looking for romantic partners online. Many of them first converse online before deciding whether or not to meet in-person. However, it is often challenging to have smooth and continuous conversations online with someone who they have never met in person. To handle this problem, we built a proof-of-concept system, Tomi, that dynamically suggests various conversation topic seeds related to the latest received messages in real-time. It selects a keyword from an incoming message and returns five contextually relevant topic seeds. In a qualitative study with eight dyads that simulated the common setting of online match-making, users could continue their conversations either by directly or indirectly utilizing the suggested topic seeds. Also, our system boosted their confidence during the chat. Lastly, we analyzed the trade-offs between several design alternatives and presented our reflections on a system supporting continuous conversations with diverse topics.