Human-AI Interaction Researcher
This empirical study acts as a primer for interested service providers, who will determine if and how Large Language Model (LLMs) technology will be used in public services for the benefit of community members and practitioners. We explore the journey of integrating an LLM in public library services through human-AI co-creation in participatory design. Conducting three iterative participatory design processes, we collaborated with 23 domain experts to pinpoint the unique challenges they face in co-creating AI agents for public service. Based on these insights, we formulated a comprehensive list of design guidelines to pave the way for effective and ethical human-AI co-creation in the service contexts. Furthermore, our research extends the existing literature on participatory design by introducing new AI-specific elements. The new framework not only enriches the current theoretical landscape but also offers a practical toolbox for designing LLM-powered public services. We demonstrate the potential of integrating AI-AI interaction into public service co-creation while taking into account the complex needs and challenges of both experts and end-users.
Pdf and open-source GitHub repo to be released soon.
This study examines the effect of using generative AI to create digital self-clones for enhancing online presentation skills. We conducted a mixed-design experiment with 44 international students and compared the use of self-videos (control group) and self-cloned videos (AI group) to practice English presentations. The self-cloned videos were generated by AI with voice clone, face swap, lip-sync, and body-language simulation based on participants’ original presentation videos, but the generated videos improved clarity and offered standard pronunciation, and logical pauses. The results showed that both groups improved their speech performance based on machine-rated scores. Even though the group difference in machine-rated improvements was not significant, results showed that the AI group demonstrated an increased depth of reflection, heightened self-compassion, emotional resonance, and a meaningful shift from a corrective to an enhancive approach to self-critique. Additionally, within the AI group, a strong congruence between participants’ self-perception and their AI self-clones led to reduced speech anxiety and greater enjoyment. Our findings suggest the ethical use of digital self-clones to augment the emotional and cognitive aspects of skill improvements.
Pdf to be released soon.
Qingxiao Zheng and Yun Huang.
RQ: How do people (e.g., victims, attackers, bystanders, or spectators) respond to safety risks posed by virtual avatars, and what are the design implications for avatar-based human-human interactions?
Understanding emerging safety risks in nuanced social VR spaces and how existing safety features are used is crucial for the future development of safe and inclusive 3D social worlds. Prior research on safety risks in social VR is mainly based on interview or survey data about social VR users’ experiences and opinions, which lacks “in-situ observations” of how individuals react to these risks. Using two empirical studies, this paper seeks to understand safety risks and safety design in social VR. In Study 1, we investigated 212 YouTube videos and their transcripts that document social VR users’ immediate experiences of safety risks as victims, attackers, or bystanders. We also analyzed spectators’ reactions to these risks shown in comments to the videos. In Study 2, we summarized 13 safety features across various social VR platforms and mapped how each existing safety feature in social VR can mitigate the risks identified in Study 1. Based on the uniqueness of social VR interaction dynamics and users’ multi-modal simulated reactions, we call for further rethinking and reapproaching safety designs for future social VR environments and propose potential design implications for future safety protection mechanisms in social VR.
RQ: How can we support multi-stakeholders to shape and create their own AI-mediated experiences?
Participatory Design (PD) aims to empower users by involving them in various design decisions. However, it was found that the PD’s evaluation criteria are usually set by the product team and used only at the end of a design process, without adequate user participation. To address this issue, we proposed introducing UX evaluation metrics into design materials at the participatory design INPUT phase. Using a case study of designing a chatbot for community members to report safety incidents, we studied the impact of this approach with 58 participants from two workshops. Our results showed that the integration of UX evaluation metrics efciently rationalized participants’ contributions and helped identify key evaluation metrics when setting values for new AI systems, enhancing PD workshop insights. In addition to examining the use of the Program Theory Model to explain PD, our empirical investigation added a new dimension to this model.
Qingxiao Zheng and Yun Huang
RQ: When and how does AI engage with humans? What are the UX effects of one-on-one (dyadic AI) and multi-party (polyadic AI) interactions?
Early conversational agents (CAs) focused on dyadic human-AI interaction between humans and the CAs, followed by the increasing popularity of polyadic human-AI interaction, in which CAs are designed to mediate human-human interactions. CAs for polyadic interactions are unique because they encompass hybrid social interactions, i.e., human-CA, human-to-human, and human-to-group behaviors. However, research on polyadic CAs is scattered across different fields, making it challenging to identify, compare, and accumulate existing knowledge. To promote the future design of CA systems, we conducted a literature review of ACM publications and identified a set of works that conducted UX (user experience) research. We qualitatively synthesized the effects of polyadic CAs into four aspects of human-human interactions, i.e., communication, engagement, connection, and relationship maintenance. Through a mixed-method analysis of the selected polyadic and dyadic CA studies, we developed a suite of evaluation measurements on the effects. Our findings show that designing with social boundaries, such as privacy, disclosure, and identification, is crucial for ethical polyadic CAs. Future research should also advance usability testing methods and trust-building guidelines for conversational AI.
Qingxiao Zheng, Yiliu Tang, Yiren Liu, Weizi Liu, and Yun Huang
RQ: How can we design a chatbot to mediate emotional communication?
Many couples experience long-distance relationships (LDRs), and “couple technologies” have been designed to influence certain relational practices or maintain them in challenging situations. Chatbots show great potential in mediating people’s interactions. However, little is known about whether and how chatbots can be desirable and effective for mediating LDRs. In this paper, we conducted a two-phase study to design and evaluate a chatbot, PocketBot, that aims to provide effective interventions for LDRs. In Phase I, we adopted an iterative design process by conducting need-finding interviews to formulate design ideas and piloted the implemented PocketBot with 11 participants. In Phase II, we evaluated PocketBot with eighteen participants (nine LDR couples) in a week-long field trial followed by exit interviews, which yielded empirical understandings of the feasibility, effectiveness, and potential pitfalls of using PocketBot. First, a knock-on-the door feature allowed couples to know when to resume an interaction after evading a conflict; this feature was preferred by certain participants (e.g., participants with stoic personalities). Second, a humor feature was introduced to spice up couples’ conversations. This feature was favored by all participants, although some couples’ perceptions of the feature varied due to their different cultural or language backgrounds. Third, a deep talk feature enabled couples at different relational stages to conduct opportunistic conversations about sensitive topics for exploring unknowns about each other, which resulted in surprising discoveries between couples who have been in relationships for years. Our findings provide inspirations for future conversational-based couple technologies that support emotional communication.
Qingxiao Zheng, Daniela Markazi, Yiliu Tang, and Yun Huang
Understanding safety risks and safety design in social VR environments Journal Article
In: Proceedings of the ACM on Human-Computer Interaction, vol. 7, no. CSCW1, pp. 1–37, 2023.
"Begin with the end in mind": Incorporating UX evaluation metrics into design materials of participatory design Proceedings Article
In: CHI EA ’23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, 2023.
UX research on conversational human-AI interaction: A literature review of the ACM digital library Proceedings Article
In: In Proceedings of the 2022 CHI conference on human factors in computing systems, 2022.
Facing the illusion and reality of safety in social VR Proceedings Article
In: CHI Conference on Human Factors in Computing Systems Extended Abstract and Proceedings of the 1st Workshop on Novel Challenges of Safety, Security and Privacy in Extended Reality, 2022.
“PocketBot is like a knock-on-the-door!”: Designing a chatbot to support long-distance relationships Journal Article
In: Proceedings of the ACM on Human-Computer Interaction, vol. 5, no. CSCW2, pp. 1–28, 2021.
Public opinion information dissemination in mobile social networks–taking Sina Weibo as an example Journal Article
In: Information Discovery and Delivery, 2020.
How interaction paradigms affect user experience and perceived interactivity in virtual reality environment Proceedings Article
In: International Conference on Human-Computer Interaction, pp. 223–234, Springer International Publishing Cham 2020.
Investigating the differences in privacy news based on grounded theory Proceedings Article
In: International Conference on Applied Human Factors and Ergonomics, pp. 528–535, Springer, Cham 2020.
How virtual reality technology influences news? Investigating VR news, TV news and text news reports in sense of presence and perceived news effects Proceedings Article
In: 69th Conference of International Communication Association (ICA2019), 2019.
My dog’s AI Clone.
🐾 Yay, You’ve Reached The Tail End! 🐶 See you next time!