Joohee Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joohee Kim has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Sungahn Ko
Pohang University of Science and Technology, Pohang, Republic of Korea
7 shared publications - Minjeong Shin
Pohang University of Science and Technology (POSTECH) Republic of Korea
5 shared publications - Hyunwook Lee
Pohang University of Science and Technology (POSTECH) Republic of Korea
4 shared publications - Bum Chul Kwon
IBM Research, Cambridge, MA, USA
3 shared publications - Daeun Jeong
Pohang University of Science and Technology (POSTECH) Republic of Korea
2 shared publications Duc M. Nguyen
UNIST (Ulsan National Institute of Science and Technology), Korea
2 shared publications
Latest Publications
- Open Access
- 11 June 2026
- Published by Wiley in Computer Graphics Forum
- p. e70450
How Do LLMs See Charts? A Comparative Study on High‐Level Visualization Comprehension in Humans and LLMs
Designers often create visualizations to achieve specific high‐level analytical or communication goals. These goals require people to extract complex and interconnected data patterns. Prior perceptual studies of visualization effectiveness have focused on low‐level tasks, such as estimating statistical quantities, and have recently explored high‐level comprehension of visualization. Despite the growing use of Large Language Models (LLMs) as visualization interpreters, how their interpretations relate to human understanding or what reasoning processes underlie their responses remains insufficiently understood. In this work, we explore LLMs' comprehension of visualization, examining the alignment between designers' communicative goals and what their audience sees. We have conducted a qualitative study to investigate the gap between human interpretative strategies and the reasoning pathways of LLMs across three types of visualizations, line graphs, bar graphs, and scatterplots, to identify the high‐level patterns generated by LLMs using three prompt conditions. Our analysis results indicate that LLMs exhibit a consistent interpretative strategy that remains unchanged across prompt constraints. Furthermore, we observe two distinct approaches: humans naturally synthesize data into trend‐centric narratives, whereas LLMs persist with a structural enumeration of comparisons and numerical ranges. Lastly, we see LLMs achieve visualization comprehension through mechanisms distinct from human intuition, pointing to critical challenges and new opportunities for visualization design.
- 11 June 2026
- Published by Wiley in Computer Graphics Forum
- p. e70450
Open AccessHow Do LLMs See Charts? A Comparative Study on High‐Level Visualization Comprehension in Humans and LLMs
Designers often create visualizations to achieve specific high‐level analytical or communication goals. These goals require people to extract complex and interconnected data patterns. Prior perceptual studies of visualization effectiveness have focused on low‐level tasks, such as estimating statistical quantities, and have recently explored high‐level comprehension of visualization. Despite the growing use of Large Language Models (LLMs) as visualization interpreters, how their interpretations relate to human understanding or what reasoning processes underlie their responses remains insufficiently understood. In this work, we explore LLMs' comprehension of visualization, examining the alignment between designers' communicative goals and what their audience sees. We have conducted a qualitative study to investigate the gap between human interpretative strategies and the reasoning pathways of LLMs across three types of visualizations, line graphs, bar graphs, and scatterplots, to identify the high‐level patterns generated by LLMs using three prompt conditions. Our analysis results indicate that LLMs exhibit a consistent interpretative strategy that remains unchanged across prompt constraints. Furthermore, we observe two distinct approaches: humans naturally synthesize data into trend‐centric narratives, whereas LLMs persist with a structural enumeration of comparisons and numerical ranges. Lastly, we see LLMs achieve visualization comprehension through mechanisms distinct from human intuition, pointing to critical challenges and new opportunities for visualization design.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
"Here, Let Me Help": An Empirical Study of User Interventions in Human–Web Agent Collaboration
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open Access"Here, Let Me Help": An Empirical Study of User Interventions in Human–Web Agent Collaboration
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
I Feel We Are Together: How People Perceive Personalized Face-Swapped GIFs in Text-Based Communication
Nonverbal cues in text-based computer-mediated communication (CMC), initially introduced to compensate for the lack of social and emotional cues, have evolved beyond their original purpose to express user identity. In particular, embodied identity cues—such as a user’s real face—remain relatively underexplored in text-based CMC despite their potential as richer cues. Recent advances in generative AI have lowered the barrier to AI-mediated self-presentation, yet empirical research is still needed to understand how these cues operate in real interactions and how users experience and accept them. To address this gap, we investigate the social and emotional effects of face-swapped GIFs (FSGIFs) created via generative AI. In a two-phase within-subjects experiment with 32 participants (16 dyads of close acquaintances), we find that FSGIFs significantly enhance relational benefits, including greater co-presence and intimacy compared to generic GIFs. Based on these findings and insights from interviews, we discuss design implications for AI-mediated self-presentation in text-based CMC.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessI Feel We Are Together: How People Perceive Personalized Face-Swapped GIFs in Text-Based Communication
Nonverbal cues in text-based computer-mediated communication (CMC), initially introduced to compensate for the lack of social and emotional cues, have evolved beyond their original purpose to express user identity. In particular, embodied identity cues—such as a user’s real face—remain relatively underexplored in text-based CMC despite their potential as richer cues. Recent advances in generative AI have lowered the barrier to AI-mediated self-presentation, yet empirical research is still needed to understand how these cues operate in real interactions and how users experience and accept them. To address this gap, we investigate the social and emotional effects of face-swapped GIFs (FSGIFs) created via generative AI. In a two-phase within-subjects experiment with 32 participants (16 dyads of close acquaintances), we find that FSGIFs significantly enhance relational benefits, including greater co-presence and intimacy compared to generic GIFs. Based on these findings and insights from interviews, we discuss design implications for AI-mediated self-presentation in text-based CMC.
- Open Access
- 2 June 2025
- Published by Cogitatio in Media and Communication
- Vol. 13
Investigating Publics’ Communicative Action in Problem Solving (CAPS) Through Data Science
This study examined the communicative action in problem solving model through data science-driven approaches to enhance the understanding of online publics’ communication behaviors. Using ChatGPT, the study analyzed YouTube comments from news channels that covered a contentious entertainment issue with multiple related events. The findings indicated that communication behaviors changed over time and manifested in diverse combinations. In addition, the study demonstrated that aware publics in the digital era were not merely passive; rather, they engaged in communication activities similar to active publics. Furthermore, it identified distinct communication behaviors associated with certain types of publics, indicating that public types also evolve dynamically across events. The results suggested that the communicative action in problem solving model served as a valuable framework for examining online communication behaviors in the digital era. Based on these insights, this study offered both academic and practical contributions to the field.
- 2 June 2025
- Published by Cogitatio in Media and Communication
- Vol. 13
Open AccessInvestigating Publics’ Communicative Action in Problem Solving (CAPS) Through Data Science
This study examined the communicative action in problem solving model through data science-driven approaches to enhance the understanding of online publics’ communication behaviors. Using ChatGPT, the study analyzed YouTube comments from news channels that covered a contentious entertainment issue with multiple related events. The findings indicated that communication behaviors changed over time and manifested in diverse combinations. In addition, the study demonstrated that aware publics in the digital era were not merely passive; rather, they engaged in communication activities similar to active publics. Furthermore, it identified distinct communication behaviors associated with certain types of publics, indicating that public types also evolve dynamically across events. The results suggested that the communicative action in problem solving model served as a valuable framework for examining online communication behaviors in the digital era. Based on these insights, this study offered both academic and practical contributions to the field.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (1) , 973-983
DG Comics: Semi-Automatically Authoring Graph Comics for Dynamic Graphs
Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs—graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG COMICS, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (1) , 973-983
DG Comics: Semi-Automatically Authoring Graph Comics for Dynamic Graphs
Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs—graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG COMICS, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review.
- Open Access
DG Comics: Semi-Automatically Authoring Graph Comics for Dynamic Graphs
Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs -- graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG Comics, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review.
Open AccessDG Comics: Semi-Automatically Authoring Graph Comics for Dynamic Graphs
Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs -- graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG Comics, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review.
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (8) , 4825-4840
Towards Visualization Thumbnail Designs That Entice Reading Data-Driven Articles
As online news increasingly include data journalism, there is a corresponding increase in the incorporation of visualization in article thumbnail images. However, little research exists on the design rationale for visualization thumbnails, such as resizing, cropping, simplifying, and embellishing charts that appear within the body of the associated article. Therefore, in this paper we aim to understand these design choices and determine what makes a visualization thumbnail inviting and interpretable. To this end, we first survey visualization thumbnails collected online and discuss visualization thumbnail practices with data journalists and news graphics designers. Based on the survey and discussion results, we then define a design space for visualization thumbnails and conduct a user study with four types of visualization thumbnails derived from the design space. The study results indicate that different chart components play different roles in attracting reader attention and enhancing reader understandability of the visualization thumbnails. We also find various thumbnail design strategies for effectively combining the charts' components, such as a data summary with highlights and data labels, and a visual legend with text labels and Human Recognizable Objects (HROs), into thumbnails. Ultimately, we distill our findings into design implications that allow effective visualization thumbnail designs for data-rich news articles. Our work can thus be seen as a first step toward providing structured guidance on how to design compelling thumbnails for data stories.
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (8) , 4825-4840
Towards Visualization Thumbnail Designs That Entice Reading Data-Driven Articles
As online news increasingly include data journalism, there is a corresponding increase in the incorporation of visualization in article thumbnail images. However, little research exists on the design rationale for visualization thumbnails, such as resizing, cropping, simplifying, and embellishing charts that appear within the body of the associated article. Therefore, in this paper we aim to understand these design choices and determine what makes a visualization thumbnail inviting and interpretable. To this end, we first survey visualization thumbnails collected online and discuss visualization thumbnail practices with data journalists and news graphics designers. Based on the survey and discussion results, we then define a design space for visualization thumbnails and conduct a user study with four types of visualization thumbnails derived from the design space. The study results indicate that different chart components play different roles in attracting reader attention and enhancing reader understandability of the visualization thumbnails. We also find various thumbnail design strategies for effectively combining the charts' components, such as a data summary with highlights and data labels, and a visual legend with text labels and Human Recognizable Objects (HROs), into thumbnails. Ultimately, we distill our findings into design implications that allow effective visualization thumbnail designs for data-rich news articles. Our work can thus be seen as a first step toward providing structured guidance on how to design compelling thumbnails for data stories.