publications

2025

1. CHI ’25

   

   Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making

   Shuai Ma, Qiaoyi Chen, Xinru Wang, Chengbo Zheng, Zhenhui Peng, Ming Yin, and Xiaojuan Ma

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025

   Abs

   Traditional AI-assisted decision-making systems often provide fixed recommendations that users must either accept or reject entirely, limiting meaningful interaction—especially in cases of disagreement. To address this, we introduce Human-AI Deliberation, an approach inspired by human deliberation theories that enables dimension-level opinion elicitation, iterative decision updates, and structured discussions between humans and AI. At the core of this approach is Deliberative AI, an assistant powered by large language models (LLMs) that facilitates flexible, conversational interactions and precise information exchange with domain-specific models. Through a mixed-methods user study, we found that Deliberative AI outperforms traditional explainable AI (XAI) systems by fostering appropriate human reliance and improving task performance. By analyzing participant perceptions, user experience, and open-ended feedback, we highlight key findings, discuss potential concerns, and explore the broader applicability of this approach for future AI-assisted decision-making systems.

2. CHI ’25

   

   InsightBridge: Enhancing Empathizing with Users through Real-Time Information Synthesis and Visual Communication

   Junze Li, Yue Zhang, Chengbo Zheng, Dingdong Liu, Zeyu Huang, and Xiaojuan Ma

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025
3. CHI ’25

   

   Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving Process

   Siyu Zha, Yujia Liu, Chengbo Zheng, Jiaqi Xu, Fuze Yu, Jiangtao Gong, and Yingqing Xu

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025

   Abs

   Creative Problem-Solving (CPS) promotes creative and critical thinking while enhancing real-world problem-solving skills, making it essential for middle school education. However, providing personalized mentorship in CPS projects at scale is challenging due to resource constraints and diverse student needs. To address this, we developed Mentigo, an AI-driven mentor agent designed to guide middle school students through the CPS process. Using a dataset of real classroom interactions, we encoded CPS task stages, adaptive guidance strategies, and personalized feedback mechanisms to inform Mentigo‘s dynamic mentoring framework powered by large language models (LLMs). A comparative experiment with 12 students and evaluations from five expert educators demonstrated improved student engagement, creativity, and task performance. Our findings highlight design implications for using LLM-based AI mentors to enhance CPS learning in educational environments.

4. CHI Workshop

   

   Supporting Data-Frame Dynamics in AI-assisted Decision Making

   Chengbo Zheng, Tim Miller, Alina Bialkowski, H Peter Soyer, and Monika Janda

   The 2025 ACM Workshop on Human-AI Interaction for Augmented Reasoning (AIREASONING-2025-01), 2025

2024

1. CHI ’24

   

   Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students

   Chengbo Zheng, Kangyu Yuan, Bingcan Guo, Reza Hadi Mogavi, Zhenhui Peng, Shuai Ma, and Xiaojuan Ma

   In Proceedings of the CHI Conference on Human Factors in Computing Systems , Honolulu, HI, USA, 2024

   Abs PDF

   Students’ increasing use of Artificial Intelligence (AI) presents new challenges for assessing their mastery of knowledge and skills in project-based learning (PBL). This paper introduces a co-design study to explore the potential of students’ AI usage data as a novel material for PBL assessment. We conducted workshops with 18 college students, encouraging them to speculate an alternative world where they could freely employ AI in PBL while needing to report this process to assess their skills and contributions. Our workshops yielded various scenarios of students’ use of AI in PBL and ways of analyzing such usage grounded by students’ vision of how educational goals may transform. We also found that students with different attitudes toward AI exhibited distinct preferences in how to analyze and understand their use of AI. Based on these findings, we discuss future research opportunities on student-AI interactions and understanding AI-enhanced learning.

2. UIST ’24

   

   DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration

   Chengbo Zheng, Yuanhao Zhang, Zeyu Huang, Chuhan Shi, Minrui Xu, and Xiaojuan Ma

   In the upcoming UIST ’24 , Pittsburgh, PA, USA, 2024

   Abs PDF Website

   Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS). Based on users’ topic of interest, DiscipLink initiates exploratory questions from the perspectives of possible relevant fields of study, and users can further tailor these questions. DiscipLink then supports users in searching and screening papers under selected questions by automatically expanding queries with disciplinary-specific terminologies, extracting themes from retrieved papers, and highlighting the connections between papers and questions. Our evaluation, comprising a within-subject comparative experiment and an open-ended exploratory study, reveals that DiscipLink can effectively support researchers in breaking down disciplinary boundaries and integrating scattered knowledge in diverse fields. The findings underscore the potential of LLM-powered tools in fostering information-seeking practices and bolstering interdisciplinary research.

3. UIST ’24

   

   WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization

   Liwenhan Xie, Chengbo Zheng, Haijun Xia, Huamin Qu, and Zhu-Tian Chen

   In the upcoming UIST ’24 , Pittsburgh, PA, USA, 2024

   Abs PDF Website

   Large language models (LLMs) have advanced data analysis through conversational interfaces, as exemplified in OpenAI’s Advanced Data Analysis. Essentially, LLMs produce code for accomplishing diverse analysis tasks. However, presenting raw code can obscure the logic and hinder user verification. To empower users with enhanced comprehension and augmented control over analysis conducted by LLMs, we propose a novel approach to transform LLM-generated code into an interactive visual representation. In the approach, users are provided with a clear, step-by-step visualization of the LLM-generated code in real time, allowing them to inspect, modify, and validate individual data operations in the analysis. Our design decisions are informed by a formative study (N=8) probing into user practice and challenges. We further developed a prototype named WaitGPT and conducted a user study (N=12) to evaluate its usability and effectiveness. The findings from the user study reveal that WaitGPT facilitates monitoring and steering of data analysis performed by LLMs, enabling participants to enhance error detection and increase their overall confidence in the results.

4. UIST ’24 Poster

   SelfGauge: An Intelligent Tool to Support Student Self-assessment in GenAI-enhanced Project-based Learning

   Chengbo Zheng, Zeyu Huang, Shuai Ma, and Xiaojuan Ma

   In UIST ’24 Poster , Pittsburgh, PA, USA, 2024
5. ChinaVis ’24

   

   A Design Space of Animating Data-Driven Transitions in Data Videos

   Chengbo Zheng, Tian Gao, Shunan Guo, Yang Shi, Xiaojuan Ma, and Nan Cao

   In ChinaVis ’24 , Hong Kong, China, 2024

   Abs PDF Website

   Data video is an increasingly popular genre of narrative visualization. To distill a data story into a video, designers need to draft a sequence of data facts and visually connect them by animated transitions. Such animated transitions are critical for illustrating data changes and enhancing narrative coherence; however, their design still lacks systematic guidance. To fill this gap, we developed a design space by collecting and analyzing 89 high-quality data videos. The design space characterizes the design of animated transitions under three dimensions: narrative relation, data change, and transition animation. We conducted an online design workshop with 14 participants to evaluate the effectiveness of our design space on designing transitions. The results show that the design patterns summarized in our design space can be used to efficiently guide the transition designs in data videos.

2023

1. 

   A Multi-Layout Design for Immersive Visualization of Network Data

   David Bauer, Chengbo Zheng, Oh-Hyun Kwon, and Kwan-Liu Ma

   2023
2. CHI ’23

   

   Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making

   Chengbo Zheng, Yuheng Wu, Chuhan Shi, Shuai Ma, Jiehui Luo, and Xiaojuan Ma

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs PDF Video

   Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making. We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an “equal AI” shed light on the possible future of human-AI relations.

3. CHI ’23

   

   RetroLens: A Human-AI Collaborative System for Multi-step Retrosynthetic Route Planning

   Chuhan Shi, Yicheng Hu, Shenan Wang, Shuai Ma, Chengbo Zheng, Xiaojuan Ma, and Qiong Luo

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs

   Multi-step retrosynthetic route planning (MRRP) is the core task in synthetic chemistry, in which chemists recursively deconstruct a target molecule to find a set of reactants that make up the target. MRRP is challenging in that the search space is vast, and chemists are often lost in the process. Existing AI models can achieve automatic MRRP fast, but they only work on relatively simple targets, which leaves complex molecules under chemists’ expertise. To facilitate MRRP of complex molecules, we proposed a human-AI collaborative system, RetroLens, through a participatory design process. AI can contribute by two approaches: joint action and algorithm-in-the-loop. Deconstruction steps are allocated to chemists or AI based on their capabilities and AI recommends candidate revision steps to fix problems along the way. A within-subjects study (N=18) showed that chemists who used RetroLens reported faster MRRP, broader design space exploration, higher confidence in their planning, and lower cognitive load.

4. CHI ’23

   

   Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making

   Shuai Ma, Ying Lei, Xinru Wang, Chengbo Zheng, Chuhan Shi, Ming Yin, and Xiaojuan Ma

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs

   In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI’s correctness likelihood (CL) but ignored humans’ CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans’ appropriate trust based on the CL of both sides at a task-instance level. We first modeled humans’ CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and effectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users’ trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confidence. We further provided practical implications for more human-compatible AI-assisted decision-making.

5. IEEE VIS ’23

   

   NL2Color: Refining Color Palettes for Charts with Natural Language

   Chuhan Shi, Weiwei Cui, Chengzhong Liu, Chengbo Zheng, Haidong Zhang, Qiong Luo, and Xiaojuan Ma

   IEEE Transactions on Visualization and Computer Graphics, Oct 2023

   Abs

   Choice of color is critical to creating effective charts with an engaging, enjoyable, and informative reading experience. However, designing a good color palette for a chart is a challenging task for novice users who lack related design expertise. For example, they often find it difficult to articulate their abstract intentions and translate these intentions into effective editing actions to achieve a desired outcome. In this work, we present NL2Color, a tool that allows novice users to refine chart color palettes using natural language expressions of their desired outcomes. We first collected and categorized a dataset of 131 triplets, each consisting of an original color palette of a chart, an editing intent, and a new color palette designed by human experts according to the intent. Our tool employs a large language model (LLM) to substitute the colors in original palettes and produce new color palettes by selecting some of the triplets as few-shot prompts. To evaluate our tool, we conducted a comprehensive two-stage evaluation, including a crowd-sourcing study (mathrmN=71) and a within-subjects user study (mathrmN=12). The results indicate that the quality of the color palettes revised by NL2Color has no significantly large difference from those designed by human experts. The participants who used NL2Color obtained revised color palettes to their satisfaction in a shorter period and with less effort.

2022

1. PacificVis ’22

   

   Evaluating the Effect of Enhanced Text-Visualization Integration on Combating Misinformation in Data Story

   Chengbo Zheng, and Xiaojuan Ma

   In 2022 IEEE 15th Pacific Visualization Symposium (PacificVis) , Apr 2022
2. CHI ’22

   

   Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work

   Chengbo Zheng^*, Dakuo Wang^*, April Yi Wang, and Xiaojuan Ma

   In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems , New Orleans, LA, USA, Apr 2022

   Abs PDF Video

   Creating presentation slides is a critical but time-consuming task for data scientists. While researchers have proposed many AI techniques to lift data scientists’ burden on data preparation and model selection, few have targeted the presentation creation task. Based on the needs identified from a formative study, this paper presents NB2Slides, an AI system that facilitates users to compose presentations of their data science work. NB2Slides uses deep learning methods as well as example-based prompts to generate slides from computational notebooks, and take users’ input (e.g., audience background) to structure the slides. NB2Slides also provides an interactive visualization that links the slides with the notebook to help users further edit the slides. A follow-up user evaluation with 12 data scientists shows that participants believed NB2Slides can improve efficiency and reduces the complexity of creating slides. Yet, participants questioned the future of full automation and suggested a human-AI collaboration paradigm.

2021

1. IEEE VIS ’20

   

   Towards Better Bus Networks: A Visual Analytics Approach

   Di Weng, Chengbo Zheng, Zikun Deng, Mingze Ma, Jie Bao, Yu Zheng, Mingliang Xu , and 1 more author

   IEEE Transactions on Visualization and Computer Graphics , Apr 2021

2025

1. CHI ’25

   

   Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making

   Shuai Ma, Qiaoyi Chen, Xinru Wang, Chengbo Zheng, Zhenhui Peng, Ming Yin, and Xiaojuan Ma

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025

   Abs

   Traditional AI-assisted decision-making systems often provide fixed recommendations that users must either accept or reject entirely, limiting meaningful interaction—especially in cases of disagreement. To address this, we introduce Human-AI Deliberation, an approach inspired by human deliberation theories that enables dimension-level opinion elicitation, iterative decision updates, and structured discussions between humans and AI. At the core of this approach is Deliberative AI, an assistant powered by large language models (LLMs) that facilitates flexible, conversational interactions and precise information exchange with domain-specific models. Through a mixed-methods user study, we found that Deliberative AI outperforms traditional explainable AI (XAI) systems by fostering appropriate human reliance and improving task performance. By analyzing participant perceptions, user experience, and open-ended feedback, we highlight key findings, discuss potential concerns, and explore the broader applicability of this approach for future AI-assisted decision-making systems.

2. CHI Workshop

   

   Supporting Data-Frame Dynamics in AI-assisted Decision Making

   Chengbo Zheng, Tim Miller, Alina Bialkowski, H Peter Soyer, and Monika Janda

   The 2025 ACM Workshop on Human-AI Interaction for Augmented Reasoning (AIREASONING-2025-01), 2025

2023

1. CHI ’23

   

   Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making

   Chengbo Zheng, Yuheng Wu, Chuhan Shi, Shuai Ma, Jiehui Luo, and Xiaojuan Ma

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs PDF Video

   Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making. We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an “equal AI” shed light on the possible future of human-AI relations.

2. CHI ’23

   

   RetroLens: A Human-AI Collaborative System for Multi-step Retrosynthetic Route Planning

   Chuhan Shi, Yicheng Hu, Shenan Wang, Shuai Ma, Chengbo Zheng, Xiaojuan Ma, and Qiong Luo

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs

   Multi-step retrosynthetic route planning (MRRP) is the core task in synthetic chemistry, in which chemists recursively deconstruct a target molecule to find a set of reactants that make up the target. MRRP is challenging in that the search space is vast, and chemists are often lost in the process. Existing AI models can achieve automatic MRRP fast, but they only work on relatively simple targets, which leaves complex molecules under chemists’ expertise. To facilitate MRRP of complex molecules, we proposed a human-AI collaborative system, RetroLens, through a participatory design process. AI can contribute by two approaches: joint action and algorithm-in-the-loop. Deconstruction steps are allocated to chemists or AI based on their capabilities and AI recommends candidate revision steps to fix problems along the way. A within-subjects study (N=18) showed that chemists who used RetroLens reported faster MRRP, broader design space exploration, higher confidence in their planning, and lower cognitive load.

3. CHI ’23

   

   Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making

   Shuai Ma, Ying Lei, Xinru Wang, Chengbo Zheng, Chuhan Shi, Ming Yin, and Xiaojuan Ma

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs

   In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI’s correctness likelihood (CL) but ignored humans’ CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans’ appropriate trust based on the CL of both sides at a task-instance level. We first modeled humans’ CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and effectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users’ trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confidence. We further provided practical implications for more human-compatible AI-assisted decision-making.

2021

1. IEEE VIS ’20

   

   Towards Better Bus Networks: A Visual Analytics Approach

   Di Weng, Chengbo Zheng, Zikun Deng, Mingze Ma, Jie Bao, Yu Zheng, Mingliang Xu , and 1 more author

   IEEE Transactions on Visualization and Computer Graphics , 2021

2025

1. CHI ’25

   

   InsightBridge: Enhancing Empathizing with Users through Real-Time Information Synthesis and Visual Communication

   Junze Li, Yue Zhang, Chengbo Zheng, Dingdong Liu, Zeyu Huang, and Xiaojuan Ma

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025

2024

1. UIST ’24

   

   DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration

   Chengbo Zheng, Yuanhao Zhang, Zeyu Huang, Chuhan Shi, Minrui Xu, and Xiaojuan Ma

   In the upcoming UIST ’24 , Pittsburgh, PA, USA, 2024

   Abs PDF Website

   Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS). Based on users’ topic of interest, DiscipLink initiates exploratory questions from the perspectives of possible relevant fields of study, and users can further tailor these questions. DiscipLink then supports users in searching and screening papers under selected questions by automatically expanding queries with disciplinary-specific terminologies, extracting themes from retrieved papers, and highlighting the connections between papers and questions. Our evaluation, comprising a within-subject comparative experiment and an open-ended exploratory study, reveals that DiscipLink can effectively support researchers in breaking down disciplinary boundaries and integrating scattered knowledge in diverse fields. The findings underscore the potential of LLM-powered tools in fostering information-seeking practices and bolstering interdisciplinary research.

2022

1. CHI ’22

   

   Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work

   Chengbo Zheng^*, Dakuo Wang^*, April Yi Wang, and Xiaojuan Ma

   In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems , New Orleans, LA, USA, 2022

   Abs PDF Video

   Creating presentation slides is a critical but time-consuming task for data scientists. While researchers have proposed many AI techniques to lift data scientists’ burden on data preparation and model selection, few have targeted the presentation creation task. Based on the needs identified from a formative study, this paper presents NB2Slides, an AI system that facilitates users to compose presentations of their data science work. NB2Slides uses deep learning methods as well as example-based prompts to generate slides from computational notebooks, and take users’ input (e.g., audience background) to structure the slides. NB2Slides also provides an interactive visualization that links the slides with the notebook to help users further edit the slides. A follow-up user evaluation with 12 data scientists shows that participants believed NB2Slides can improve efficiency and reduces the complexity of creating slides. Yet, participants questioned the future of full automation and suggested a human-AI collaboration paradigm.

2025

1. CHI ’25

   

   Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving Process

   Siyu Zha, Yujia Liu, Chengbo Zheng, Jiaqi Xu, Fuze Yu, Jiangtao Gong, and Yingqing Xu

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems , Yokohama, Japan, 2025

   Abs

   Creative Problem-Solving (CPS) promotes creative and critical thinking while enhancing real-world problem-solving skills, making it essential for middle school education. However, providing personalized mentorship in CPS projects at scale is challenging due to resource constraints and diverse student needs. To address this, we developed Mentigo, an AI-driven mentor agent designed to guide middle school students through the CPS process. Using a dataset of real classroom interactions, we encoded CPS task stages, adaptive guidance strategies, and personalized feedback mechanisms to inform Mentigo‘s dynamic mentoring framework powered by large language models (LLMs). A comparative experiment with 12 students and evaluations from five expert educators demonstrated improved student engagement, creativity, and task performance. Our findings highlight design implications for using LLM-based AI mentors to enhance CPS learning in educational environments.

2024

1. CHI ’24

   

   Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students

   Chengbo Zheng, Kangyu Yuan, Bingcan Guo, Reza Hadi Mogavi, Zhenhui Peng, Shuai Ma, and Xiaojuan Ma

   In Proceedings of the CHI Conference on Human Factors in Computing Systems , Honolulu, HI, USA, 2024

   Abs PDF

   Students’ increasing use of Artificial Intelligence (AI) presents new challenges for assessing their mastery of knowledge and skills in project-based learning (PBL). This paper introduces a co-design study to explore the potential of students’ AI usage data as a novel material for PBL assessment. We conducted workshops with 18 college students, encouraging them to speculate an alternative world where they could freely employ AI in PBL while needing to report this process to assess their skills and contributions. Our workshops yielded various scenarios of students’ use of AI in PBL and ways of analyzing such usage grounded by students’ vision of how educational goals may transform. We also found that students with different attitudes toward AI exhibited distinct preferences in how to analyze and understand their use of AI. Based on these findings, we discuss future research opportunities on student-AI interactions and understanding AI-enhanced learning.

2023

1. CHI ’23

   

   Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making

   Chengbo Zheng, Yuheng Wu, Chuhan Shi, Shuai Ma, Jiehui Luo, and Xiaojuan Ma

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , Hamburg, Germany, 2023

   Abs PDF Video

   Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making. We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an “equal AI” shed light on the possible future of human-AI relations.

2024

1. UIST ’24

   

   WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization

   Liwenhan Xie, Chengbo Zheng, Haijun Xia, Huamin Qu, and Zhu-Tian Chen

   In the upcoming UIST ’24 , Pittsburgh, PA, USA, 2024

   Abs PDF Website

   Large language models (LLMs) have advanced data analysis through conversational interfaces, as exemplified in OpenAI’s Advanced Data Analysis. Essentially, LLMs produce code for accomplishing diverse analysis tasks. However, presenting raw code can obscure the logic and hinder user verification. To empower users with enhanced comprehension and augmented control over analysis conducted by LLMs, we propose a novel approach to transform LLM-generated code into an interactive visual representation. In the approach, users are provided with a clear, step-by-step visualization of the LLM-generated code in real time, allowing them to inspect, modify, and validate individual data operations in the analysis. Our design decisions are informed by a formative study (N=8) probing into user practice and challenges. We further developed a prototype named WaitGPT and conducted a user study (N=12) to evaluate its usability and effectiveness. The findings from the user study reveal that WaitGPT facilitates monitoring and steering of data analysis performed by LLMs, enabling participants to enhance error detection and increase their overall confidence in the results.

2. ChinaVis ’24

   

   A Design Space of Animating Data-Driven Transitions in Data Videos

   Chengbo Zheng, Tian Gao, Shunan Guo, Yang Shi, Xiaojuan Ma, and Nan Cao

   In ChinaVis ’24 , Hong Kong, China, 2024

   Abs PDF Website

   Data video is an increasingly popular genre of narrative visualization. To distill a data story into a video, designers need to draft a sequence of data facts and visually connect them by animated transitions. Such animated transitions are critical for illustrating data changes and enhancing narrative coherence; however, their design still lacks systematic guidance. To fill this gap, we developed a design space by collecting and analyzing 89 high-quality data videos. The design space characterizes the design of animated transitions under three dimensions: narrative relation, data change, and transition animation. We conducted an online design workshop with 14 participants to evaluate the effectiveness of our design space on designing transitions. The results show that the design patterns summarized in our design space can be used to efficiently guide the transition designs in data videos.

2023

1. 

   A Multi-Layout Design for Immersive Visualization of Network Data

   David Bauer, Chengbo Zheng, Oh-Hyun Kwon, and Kwan-Liu Ma

   2023
2. IEEE VIS ’23

   

   NL2Color: Refining Color Palettes for Charts with Natural Language

   Chuhan Shi, Weiwei Cui, Chengzhong Liu, Chengbo Zheng, Haidong Zhang, Qiong Luo, and Xiaojuan Ma

   IEEE Transactions on Visualization and Computer Graphics, Oct 2023

   Abs

   Choice of color is critical to creating effective charts with an engaging, enjoyable, and informative reading experience. However, designing a good color palette for a chart is a challenging task for novice users who lack related design expertise. For example, they often find it difficult to articulate their abstract intentions and translate these intentions into effective editing actions to achieve a desired outcome. In this work, we present NL2Color, a tool that allows novice users to refine chart color palettes using natural language expressions of their desired outcomes. We first collected and categorized a dataset of 131 triplets, each consisting of an original color palette of a chart, an editing intent, and a new color palette designed by human experts according to the intent. Our tool employs a large language model (LLM) to substitute the colors in original palettes and produce new color palettes by selecting some of the triplets as few-shot prompts. To evaluate our tool, we conducted a comprehensive two-stage evaluation, including a crowd-sourcing study (mathrmN=71) and a within-subjects user study (mathrmN=12). The results indicate that the quality of the color palettes revised by NL2Color has no significantly large difference from those designed by human experts. The participants who used NL2Color obtained revised color palettes to their satisfaction in a shorter period and with less effort.

2022

1. PacificVis ’22

   

   Evaluating the Effect of Enhanced Text-Visualization Integration on Combating Misinformation in Data Story

   Chengbo Zheng, and Xiaojuan Ma

   In 2022 IEEE 15th Pacific Visualization Symposium (PacificVis) , Apr 2022

2021

1. IEEE VIS ’20

   

   Towards Better Bus Networks: A Visual Analytics Approach

   Di Weng, Chengbo Zheng, Zikun Deng, Mingze Ma, Jie Bao, Yu Zheng, Mingliang Xu , and 1 more author

   IEEE Transactions on Visualization and Computer Graphics , Apr 2021