Xiaohang Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaohang Tang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Yan Chen
Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA
7 shared publications - Sam Wong
University of Washington, Seattle, Washington, USA
4 shared publications - Xi Chen
Department of Computer Science, Virginia Tech, United States
3 shared publications - Ge Zhang
University of Michigan, Ann Arbor, Michigan, USA
2 shared publications - Steve Oney
School of Information, University of Michigan, Ann Arbor, Michigan, USA
2 shared publications - Xiang Li
Department of Engineering, University of Cambridge, Cambridge, United Kingdom
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessTutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
SPHERE: Supporting Personalized Feedback at Scale in Programming Classrooms with Structured Review of Generative AI Outputs
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessSPHERE: Supporting Personalized Feedback at Scale in Programming Classrooms with Structured Review of Generative AI Outputs
- Open Access
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1260-1266
The Impact of Group Discussion and Formation on Student Performance: An Experience Report in a Large CS1 Course
Programming instructors often conduct collaborative learning activities, such as Peer Instruction (PI), to enhance student motivation, engagement, and learning gains. However, the impact of group discussion and formation mechanisms on student performance remains unclear. To investigate this, we conducted an 11-session experiment in a large, in-person CS1 course. We employed both random and expertise-balanced grouping methods to examine the efficacy of different group mechanisms and the impact of expert students' presence on collaborative learning. Our observations revealed complex dynamics within the collaborative learning environment. Among 255 groups, 146 actively engaged in discussions, with 96 of these groups demonstrating improvement for poor-performing students. Interestingly, our analysis revealed that different grouping methods (expertise-balanced or random) did not significantly influence discussion engagement or poor-performing students' improvement. In our deeper qualitative analysis, we found that struggling students often derived benefits from interactions with expert peers, but this positive effect was not consistent across all groups. We identified challenges that expert students face in peer instruction interactions, highlighting the complexity of leveraging expertise within group discussions.
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1260-1266
Open AccessThe Impact of Group Discussion and Formation on Student Performance: An Experience Report in a Large CS1 Course
Programming instructors often conduct collaborative learning activities, such as Peer Instruction (PI), to enhance student motivation, engagement, and learning gains. However, the impact of group discussion and formation mechanisms on student performance remains unclear. To investigate this, we conducted an 11-session experiment in a large, in-person CS1 course. We employed both random and expertise-balanced grouping methods to examine the efficacy of different group mechanisms and the impact of expert students' presence on collaborative learning. Our observations revealed complex dynamics within the collaborative learning environment. Among 255 groups, 146 actively engaged in discussions, with 96 of these groups demonstrating improvement for poor-performing students. Interestingly, our analysis revealed that different grouping methods (expertise-balanced or random) did not significantly influence discussion engagement or poor-performing students' improvement. In our deeper qualitative analysis, we found that struggling students often derived benefits from interactions with expert peers, but this positive effect was not consistent across all groups. We identified challenges that expert students face in peer instruction interactions, highlighting the complexity of leveraging expertise within group discussions.
- Open Access
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-22
VizGroup: An AI-assisted Event-driven System for Collaborative Programming Learning Analytics
Programming instructors often conduct collaborative learning activities, like Peer Instruction, to foster a deeper understanding in students and enhance their engagement with learning. These activities, however, may not always yield productive outcomes due to the diversity of student mental models and their ineffective collaboration. In this work, we introduce VizGroup, an AI-assisted system that enables programming instructors to easily oversee students’ real-time collaborative learning behaviors during large programming courses. VizGroup leverages Large Language Models (LLMs) to recommend event specifications for instructors so that they can simultaneously track and receive alerts about key correlation patterns between various collaboration metrics and ongoing coding tasks. We evaluated VizGroup with 12 instructors in a comparison study using a dataset collected from a Peer Instruction activity that was conducted in a large programming lecture. The results showed that VizGroup helped instructors effectively overview, narrow down, and track nuances throughout students’ behaviors.
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessVizGroup: An AI-assisted Event-driven System for Collaborative Programming Learning Analytics
Programming instructors often conduct collaborative learning activities, like Peer Instruction, to foster a deeper understanding in students and enhance their engagement with learning. These activities, however, may not always yield productive outcomes due to the diversity of student mental models and their ineffective collaboration. In this work, we introduce VizGroup, an AI-assisted system that enables programming instructors to easily oversee students’ real-time collaborative learning behaviors during large programming courses. VizGroup leverages Large Language Models (LLMs) to recommend event specifications for instructors so that they can simultaneously track and receive alerts about key correlation patterns between various collaboration metrics and ongoing coding tasks. We evaluated VizGroup with 12 instructors in a comparison study using a dataset collected from a Peer Instruction activity that was conducted in a large programming lecture. The results showed that VizGroup helped instructors effectively overview, narrow down, and track nuances throughout students’ behaviors.
- Open Access
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 188-199
CFlow: Supporting Semantic Flow Analysis of Students' Code in Programming Problems at Scale
Introductory programming courses have been growing rapidly, now enrolling hundreds or thousands of students. In such large courses, it can be overwhelmingly difficult for instructors to understand class-wide problem-solving patterns or issues, which is crucial for improving instruction and addressing important pedagogical challenges. In this paper, we propose a technique and system, CFlow, for creating understandable and navigable representations of code at scale. CFlow is able to represent thousands of code samples in a visualization that resembles a single code sample. CFlow creates scalable code representations by (1) clustering individual statements with similar semantic purposes, (2) presenting clustered statements in a way that maintains semantic relationships between statements, (3) representing the correctness of different variations as a histogram, and (4) allowing users to navigate through solutions interactively using semantic filters. With a multi-level view design, users can navigate high-level patterns, and low-level implementations. This is in contrast to prior tools that either limit their focus on isolated statements (and thus discard the surrounding context of those statements) or cluster entire code samples (which can lead to large numbers of clusters---for example, if there are n code features and m implementations of each, there can be mn clusters). We evaluated the effectiveness of CFlow with a comparison study, found participants using CFlow spent only half the time identifying mistakes and recalled twice as many desired patterns from over 6,000 submissions.
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 188-199
Open AccessCFlow: Supporting Semantic Flow Analysis of Students' Code in Programming Problems at Scale
Introductory programming courses have been growing rapidly, now enrolling hundreds or thousands of students. In such large courses, it can be overwhelmingly difficult for instructors to understand class-wide problem-solving patterns or issues, which is crucial for improving instruction and addressing important pedagogical challenges. In this paper, we propose a technique and system, CFlow, for creating understandable and navigable representations of code at scale. CFlow is able to represent thousands of code samples in a visualization that resembles a single code sample. CFlow creates scalable code representations by (1) clustering individual statements with similar semantic purposes, (2) presenting clustered statements in a way that maintains semantic relationships between statements, (3) representing the correctness of different variations as a histogram, and (4) allowing users to navigate through solutions interactively using semantic filters. With a multi-level view design, users can navigate high-level patterns, and low-level implementations. This is in contrast to prior tools that either limit their focus on isolated statements (and thus discard the surrounding context of those statements) or cluster entire code samples (which can lead to large numbers of clusters---for example, if there are n code features and m implementations of each, there can be mn clusters). We evaluated the effectiveness of CFlow with a comparison study, found participants using CFlow spent only half the time identifying mistakes and recalled twice as many desired patterns from over 6,000 submissions.
- Open Access
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 542-543
Demonstration of CFlow: Supporting Semantic Flow Analysis of Students' Code in Programming Problems at Scale
Introductory programming courses have been growing rapidly, now enrolling hundreds or thousands of students. In such large courses, it can be overwhelmingly difficult for instructors to understand class-wide problem-solving patterns or issues, which is crucial for improving instruction and addressing important pedagogical challenges. In this paper, we propose a technique and system, CFlow, for creating understandable and navigable representations of code at scale. CFlow is able to represent thousands of code samples in a visualization that resembles a single code sample. CFlow creates scalable code representations by (1) clustering individual statements with similar semantic purposes, (2) presenting clustered statements in a way that maintains semantic relationships between statements, (3) representing the correctness of different variations as a histogram, and (4) allowing users to navigate through solutions interactively using semantic filters. With a multi-level view design, users can navigate high-level patterns, and low-level implementations. This is in contrast to prior tools that either limit their focus on isolated statements (and thus discard the surrounding context of those statements) or cluster entire code samples (which can lead to large numbers of clusters---for example, if there are n code features and m implementations of each, there can be m^n clusters).
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 542-543
Open AccessDemonstration of CFlow: Supporting Semantic Flow Analysis of Students' Code in Programming Problems at Scale
Introductory programming courses have been growing rapidly, now enrolling hundreds or thousands of students. In such large courses, it can be overwhelmingly difficult for instructors to understand class-wide problem-solving patterns or issues, which is crucial for improving instruction and addressing important pedagogical challenges. In this paper, we propose a technique and system, CFlow, for creating understandable and navigable representations of code at scale. CFlow is able to represent thousands of code samples in a visualization that resembles a single code sample. CFlow creates scalable code representations by (1) clustering individual statements with similar semantic purposes, (2) presenting clustered statements in a way that maintains semantic relationships between statements, (3) representing the correctness of different variations as a histogram, and (4) allowing users to navigate through solutions interactively using semantic filters. With a multi-level view design, users can navigate high-level patterns, and low-level implementations. This is in contrast to prior tools that either limit their focus on isolated statements (and thus discard the surrounding context of those statements) or cluster entire code samples (which can lead to large numbers of clusters---for example, if there are n code features and m implementations of each, there can be m^n clusters).
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
VizPI: A Real-Time Visualization Tool for Enhancing Peer Instruction in Large-Scale Programming Lectures
Peer instruction (PI) has shown significant potential in facilitating student engagement and collaborative learning. However, the implementation of PI for large-scale programming lectures has proven challenging due to difficulties in monitoring student engagement, discussion topics, and code changes. This paper introduces VizPI, an interactive web tool that enables instructors to conduct, monitor, and assess PI for programming exercises in real-time. With features that visualize the progress of student discussions and code submissions, VizPI allows for more effective oversight of PI activities and the provision of personalized feedback at scale. Our work aims to transform the pedagogical approach to PI in programming education, making it more engaging and adaptable to student needs.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessVizPI: A Real-Time Visualization Tool for Enhancing Peer Instruction in Large-Scale Programming Lectures
Peer instruction (PI) has shown significant potential in facilitating student engagement and collaborative learning. However, the implementation of PI for large-scale programming lectures has proven challenging due to difficulties in monitoring student engagement, discussion topics, and code changes. This paper introduces VizPI, an interactive web tool that enables instructors to conduct, monitor, and assess PI for programming exercises in real-time. With features that visualize the progress of student discussions and code submissions, VizPI allows for more effective oversight of PI activities and the provision of personalized feedback at scale. Our work aims to transform the pedagogical approach to PI in programming education, making it more engaging and adaptable to student needs.
- Open Access
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-2
GesMessages: Using Mid-air Gestures to Manage Notifications
This paper introduces GesMessages, an innovative mid-air interactive application that uses simple gestures to manage real-time message notifications on laptops and large displays. Leveraging cameras on computers or smart devices, the application offers three distinct gestures: expanding notifications for immediate attention, hiding non-urgent messages, and deleting spam messages. We present the technical setup and system design. Additionally, we explore potential applications in context-awareness systems, contributing to gestural interaction research. Our work fosters a deeper understanding of mid-air interaction’s impact on message management and future interactive systems.
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessGesMessages: Using Mid-air Gestures to Manage Notifications
This paper introduces GesMessages, an innovative mid-air interactive application that uses simple gestures to manage real-time message notifications on laptops and large displays. Leveraging cameras on computers or smart devices, the application offers three distinct gestures: expanding notifications for immediate attention, hiding non-urgent messages, and deleting spam messages. We present the technical setup and system design. Additionally, we explore potential applications in context-awareness systems, contributing to gestural interaction research. Our work fosters a deeper understanding of mid-air interaction’s impact on message management and future interactive systems.
- Top Cited PapersOpen Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-19
PaTAT: Human-AI Collaborative Qualitative Coding with Explainable Interactive Rule Synthesis
Over the years, the task of AI-assisted data annotation has seen remarkable advancements. However, a specific type of annotation task, the qualitative coding performed during thematic analysis, has characteristics that make effective human-AI collaboration difficult. Informed by a formative study, we designed PaTAT, a new AI-enabled tool that uses an interactive program synthesis approach to learn flexible and expressive patterns over user-annotated codes in real-time as users annotate data. To accommodate the ambiguous, uncertain, and iterative nature of thematic analysis, the use of user-interpretable patterns allows users to understand and validate what the system has learned, make direct fixes, and easily revise, split, or merge previously annotated codes. This new approach also helps human users to learn data characteristics and form new theories in addition to facilitating the “learning” of the AI model. PaTAT’s usefulness and effectiveness were evaluated in a lab user study.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Top Cited PapersOpen AccessPaTAT: Human-AI Collaborative Qualitative Coding with Explainable Interactive Rule Synthesis
Over the years, the task of AI-assisted data annotation has seen remarkable advancements. However, a specific type of annotation task, the qualitative coding performed during thematic analysis, has characteristics that make effective human-AI collaboration difficult. Informed by a formative study, we designed PaTAT, a new AI-enabled tool that uses an interactive program synthesis approach to learn flexible and expressive patterns over user-annotated codes in real-time as users annotate data. To accommodate the ambiguous, uncertain, and iterative nature of thematic analysis, the use of user-interpretable patterns allows users to understand and validate what the system has learned, make direct fixes, and easily revise, split, or merge previously annotated codes. This new approach also helps human users to learn data characteristics and form new theories in addition to facilitating the “learning” of the AI model. PaTAT’s usefulness and effectiveness were evaluated in a lab user study.
- Open Access
- 20 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 4-8
GesPlayer: Using Augmented Gestures to Empower Video Players
In this paper, we introduce GesPlayer, a gesture-based empowered video player that explores how users can experience their hands as an interface through gestures. We provide three semantic gestures based on the camera of a computer or other smart device to detect and adjust the progress of video playback, volume, and screen brightness, respectively. Our goal is to enable users to control video playback simply by their gestures in the air, without the need to use a mouse or keyboard, especially when it is not convenient to do so. Ultimately, we hope to expand our understanding of gesture-based interaction by understanding the inclusiveness of designing the hand as an interactive interface, and further broaden the state of semantic gestures in an interactive environment through computational interaction methods.
- 20 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 4-8
Open AccessGesPlayer: Using Augmented Gestures to Empower Video Players
In this paper, we introduce GesPlayer, a gesture-based empowered video player that explores how users can experience their hands as an interface through gestures. We provide three semantic gestures based on the camera of a computer or other smart device to detect and adjust the progress of video playback, volume, and screen brightness, respectively. Our goal is to enable users to control video playback simply by their gestures in the air, without the need to use a mouse or keyboard, especially when it is not convenient to do so. Ultimately, we hope to expand our understanding of gesture-based interaction by understanding the inclusiveness of designing the hand as an interactive interface, and further broaden the state of semantic gestures in an interactive environment through computational interaction methods.