Pengcheng An
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
Pengcheng An has a total of 239 co-authors. Here are the top co-authors by number of shared publications:
- Jian Zhao
School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada
12 shared publications - Di Liu
School of Design, Southern University of Science and Technology, Shenzhen, China
7 shared publications - Jun Hu
Industrial Design, Eindhoven University of Technology, Eindhoven, Netherlands
6 shared publications - Hanqing Zhou
School of Design, Southern University of Science and Technology, Shenzhen, China
5 shared publications - Jiaqi Jiang
School of Design, Southern University of Science and Technology, Shenzhen, China
5 shared publications - Qi Wang
Tongji University
4 shared publications
Latest Publications
- Open Access
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 32-37
From Home to Housing: Designing Smart Home Care Ecologies
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 32-37
Open AccessFrom Home to Housing: Designing Smart Home Care Ecologies
- Open Access
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 78-81
Human-Centered AI for Expressive Arts Therapy: Designing for Mental Well-Being and Creativity
Expressive arts therapy supports creative expression through visual art, music, dance, and drama, fostering emotional awareness, regulation, and personal growth. Recent advances in generative AI, particularly multimodal models that produce images, music, text, and soundscapes, create new opportunities to scaffold creative exploration, provide adaptive prompts, and support reflective dialogue in therapeutic contexts. At the same time, integrating AI into expressive arts therapy raises important challenges around agency, authorship, emotional alignment, ethics, data privacy, and preserving therapeutic relationships. This workshop brings together researchers, designers, therapists, and practitioners to explore how human-centered AI can support creativity in art and music therapy while respecting therapeutic values. We focus on insights from AI-enabled therapy systems, design approaches balancing creativity and emotional well-being, and evaluation methods that extend beyond usability and traditional clinical outcomes. Through interdisciplinary discussion, the workshop aims to surface open research questions and design considerations for AI use in expressive arts therapy.
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 78-81
Open AccessHuman-Centered AI for Expressive Arts Therapy: Designing for Mental Well-Being and Creativity
Expressive arts therapy supports creative expression through visual art, music, dance, and drama, fostering emotional awareness, regulation, and personal growth. Recent advances in generative AI, particularly multimodal models that produce images, music, text, and soundscapes, create new opportunities to scaffold creative exploration, provide adaptive prompts, and support reflective dialogue in therapeutic contexts. At the same time, integrating AI into expressive arts therapy raises important challenges around agency, authorship, emotional alignment, ethics, data privacy, and preserving therapeutic relationships. This workshop brings together researchers, designers, therapists, and practitioners to explore how human-centered AI can support creativity in art and music therapy while respecting therapeutic values. We focus on insights from AI-enabled therapy systems, design approaches balancing creativity and emotional well-being, and evaluation methods that extend beyond usability and traditional clinical outcomes. Through interdisciplinary discussion, the workshop aims to surface open research questions and design considerations for AI use in expressive arts therapy.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Novobo: Supporting Teachers' Peer Learning of Instructional Gestures by Teaching a Mentee AI-Agent Together
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessNovobo: Supporting Teachers' Peer Learning of Instructional Gestures by Teaching a Mentee AI-Agent Together
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Agentic Audio Moderator vs Human Moderator in Think-Aloud Usability Testing: Results from a Randomized Controlled Trial
Agentic AI holds promise for usability testing, yet its role as an audio moderator in think-aloud protocols is not well understood. This study explores: (1) how to design and develop an agentic audio moderator for think-aloud usability testing, and (2) how participants moderated by an agentic moderator differ from those moderated by a human regarding task performance, verbalization behaviors, user experience, and social perceptions of the moderator. Using a design-based research approach, we interviewed nine UX experts, iteratively developed an AI moderator, and evaluated it in a randomized controlled trial (N = 60) with a note-taking application. Results suggest that significant differences were not observed between AI and human moderators in task performance or verbalization behaviors, though AI moderators received lower social perception ratings. This work contributes the first design-oriented evaluation of AI moderators in usability testing, offering implications for developing more acceptable and effective agentic audio moderators.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessAgentic Audio Moderator vs Human Moderator in Think-Aloud Usability Testing: Results from a Randomized Controlled Trial
Agentic AI holds promise for usability testing, yet its role as an audio moderator in think-aloud protocols is not well understood. This study explores: (1) how to design and develop an agentic audio moderator for think-aloud usability testing, and (2) how participants moderated by an agentic moderator differ from those moderated by a human regarding task performance, verbalization behaviors, user experience, and social perceptions of the moderator. Using a design-based research approach, we interviewed nine UX experts, iteratively developed an AI moderator, and evaluated it in a randomized controlled trial (N = 60) with a note-taking application. Results suggest that significant differences were not observed between AI and human moderators in task performance or verbalization behaviors, though AI moderators received lower social perception ratings. This work contributes the first design-oriented evaluation of AI moderators in usability testing, offering implications for developing more acceptable and effective agentic audio moderators.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
When Generative AI Is Intimate, Sexy, and Violent: Examining Not-Safe-For-Work (NSFW) Chatbots on FlowGPT
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessWhen Generative AI Is Intimate, Sexy, and Violent: Examining Not-Safe-For-Work (NSFW) Chatbots on FlowGPT
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
GenMemo: Exploring Narrative Chaining Visual Mnemonics to Support Memorization of Structured Proposition Texts
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessGenMemo: Exploring Narrative Chaining Visual Mnemonics to Support Memorization of Structured Proposition Texts
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
ASafePlace: User-Led Personalization of VR Relaxation via an Art Therapy Activity
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Open AccessASafePlace: User-Led Personalization of VR Relaxation via an Art Therapy Activity
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
HeriTell: Supporting Interactive Documentation of Cultural Heritage Knowledge through Spatial Authoring
Cultural heritage knowledge is often interpretive, relational, and tied to spatial context, yet it is typically documented through 2D records that separate this knowledge from three-dimensional representations. We present HeriTell, a VR-based technology probe that supports spatially situated, voice-based authoring of interpretive heritage knowledge. Experts reference architectural components directly in VR and articulate interpretations through natural language narration, which is minimally parsed and anchored as spatial annotations. A formative study with heritage experts examines current documentation practices, the types of knowledge captured through spatial authoring, and scenarios where this approach is most valuable. Our findings suggest spatial authoring may better align with experts’ situated interpretive practices, and provide initial insights into how immersive systems could support expert-centered documentation in cultural heritage HCI.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessHeriTell: Supporting Interactive Documentation of Cultural Heritage Knowledge through Spatial Authoring
Cultural heritage knowledge is often interpretive, relational, and tied to spatial context, yet it is typically documented through 2D records that separate this knowledge from three-dimensional representations. We present HeriTell, a VR-based technology probe that supports spatially situated, voice-based authoring of interpretive heritage knowledge. Experts reference architectural components directly in VR and articulate interpretations through natural language narration, which is minimally parsed and anchored as spatial annotations. A formative study with heritage experts examines current documentation practices, the types of knowledge captured through spatial authoring, and scenarios where this approach is most valuable. Our findings suggest spatial authoring may better align with experts’ situated interpretive practices, and provide initial insights into how immersive systems could support expert-centered documentation in cultural heritage HCI.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
ProjecTA: A Semi-Humanoid Robotic Teaching Assistant with In-Situ Projection for Guided Tours
Robotic teaching assistants (TAs) often use body-mounted screens to deliver content. In nomadic, walk-and-talk learning, such as tours in makerspaces, these screens can distract learners from real-world objects, increasing extraneous cognitive load. HCI research lacks empirical comparisons of potential alternatives, such as robots with in-situ projection versus screen-based counterparts; little knowledge has been derived for designing such alternatives. We introduce ProjecTA, a semi-humanoid, gesture-capable TA that guides learners while projecting near-object overlays coordinated with speech and gestures. In a mixed-method study (N=24) in a university makerspace, ProjecTA significantly reduced extraneous load and outperformed its screen-based counterpart in perceived usability, usefulness of visual display, and cross-modal complementarity. Qualitative analyses revealed how ProjecTA’s coordinated projections, gestures and speech anchored explanations in place and time, enhancing understanding in ways a screen could not. We derive key design implications for future robotic TAs leveraging spatial projection to support mobile learning in physical environments.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Open AccessProjecTA: A Semi-Humanoid Robotic Teaching Assistant with In-Situ Projection for Guided Tours
Robotic teaching assistants (TAs) often use body-mounted screens to deliver content. In nomadic, walk-and-talk learning, such as tours in makerspaces, these screens can distract learners from real-world objects, increasing extraneous cognitive load. HCI research lacks empirical comparisons of potential alternatives, such as robots with in-situ projection versus screen-based counterparts; little knowledge has been derived for designing such alternatives. We introduce ProjecTA, a semi-humanoid, gesture-capable TA that guides learners while projecting near-object overlays coordinated with speech and gestures. In a mixed-method study (N=24) in a university makerspace, ProjecTA significantly reduced extraneous load and outperformed its screen-based counterpart in perceived usability, usefulness of visual display, and cross-modal complementarity. Qualitative analyses revealed how ProjecTA’s coordinated projections, gestures and speech anchored explanations in place and time, enhancing understanding in ways a screen could not. We derive key design implications for future robotic TAs leveraging spatial projection to support mobile learning in physical environments.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
DOLLama: Fostering Family Anti-Bullying Learning through AI-Augmented, Toy-Mediated Educational Drama
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessDOLLama: Fostering Family Anti-Bullying Learning through AI-Augmented, Toy-Mediated Educational Drama