In the rapidly evolving field of artificial intelligence (AI) agents, designing the agent's characteristics is crucial for shaping user experience. This workshop aims to establish a research community focused on AI agent persona design for various contexts, such as in-car assistants, educational tools, and smart home environments. We will explore critical aspects of persona design, such as voice, embodiment, and demographics, and their impact on user satisfaction and engagement. Through discussions and hands-on activities, we aim to propose practices and standards that enhance the ecological validity of agent personas. Topics include the design of conversational interfaces, the influence of agent personas on user experience, and approaches for creating contextually appropriate AI agents. This workshop will provide a platform for building a community dedicated to developing AI agent personas that better fit diverse, everyday interactions.
Join us for a full-day in-person workshop to advance the discourse on Enhancing Human-Agent Interaction Through Thoughtful Persona Design at MUM 2024 in Stockholm.
How should AI agents look? How should they communicate? How should they interact with people? Ultimately, how should their experiential side be designed?
These are key questions in the fast-evolving field of AI agents, where the design and representation of agent personas play a vital role in shaping user interactions and experiences. We aim to bring together experts from diverse disciplines to explore and discuss the design of conversational AI agent personas across various contexts, such as in-car assistants, educational support tools, or smart home environments.
We encourage the submission of position papers (2-4 pages in ACM single-column format, including references) that present research findings, innovative ideas, and work-in-progress related to AI agent persona design. We also welcome expressions of interest from those who may not have formal papers but wish to contribute to the workshop.
Dr. Hannah Pelikan is a PostDoc in the division of Language, Culture, and Interaction at Linköping University, working in the WASP-HS AI in Motion project with professors Barry Brown and Mathias Broth. Her work is located at the intersection of conversation analysis and interaction design and was honoured with two best paper awards (ACM/IEEE HRI, ACM CSCW) and one ACM best paper nomination (HRI). Her PhD thesis on sound design for robots was selected for presentation at the HRI Pioneers workshop, which gathers the world’s top student researchers in Human-Robot Interaction. Hannah is engaged in multiple international research projects and has received funding from the Swedish Innovation Agency for her collaboration with Cornell University and from Responsible AI UK for her collaboration with the University of Nottingham. Hannah regularly speaks at popular science events such as Pint of Science and Forskarfredag and her work has been featured in several press releases, including the Cornell Chronicle, Elektroniktidningen and University of Nottingham’s 100 Ways to Change the World.
Welcome and Agenda
9:00 AM - 9:30 AM
Keynote
9:30 AM - 10:30 AM
Coffee ☕
Presentations
11:00 AM - 11:30 PM
Expressive AI Agent Persona Demonstration
11:30 AM - 12:30 PM
Lunch 🍕
Prototyping Activity
13:30 AM - 15:00 PM
Coffee ☕
Conclusion and Closing
15:30 AM - 16:00 PM
We are excited about the organisation committee of this workshop with expertise in diverse fields. Together, the organisers have a history in a variety of topics including human-robot interaction, natural language processing, conversational user interfaces, dark patterns, multi-modal communication, as well as pervasive and persuasive technologies. Below, we would like to introduce each co-organisator individually.
Nima Zargham is a postdoctoral researcher in the Digital Media Lab at the University of Bremen. His research focuses on human-centered approaches for designing speech-based systems that elicit desirable user experiences. Nima has previously organized CUI-related workshops at notable conferences such as ACM/IEEE HRI 2023, ACM CUI 2023, ACM CUI 2024, and ACM CHI 24. Additionally, he served as a local chair at the ACM CHI-PLAY 2022 conference. His research efforts have resulted in publications featured in prestigious HCI venues, including CHI, CUI, and CHI-PLAY.
Mateusz Dubiel is a research associate in the Department of Computer Science at the University of Luxembourg, where he works on developing and evaluating conversational agents. Specifically, his current research focuses on assessing the cognitive and usability implications of interfaces that feature speech and exploring their potential to inspire positive behavioral change in users. He served as Short Papers Chair for CUI '22 and was one of the General Chairs for CUI '24.
Smit Desai is a postdoctoral researcher in the College of Art, Media and Design at the Northeastern University, Boston. His primary research focus centers around comprehending the mental models of users as they engage with conversational agents, utilizing innovative research techniques such as metaphor analysis. He leverages this valuable insight to advance the development of conversational agents in diverse social roles, including educators and storytellers. His research has yielded publications in esteemed HCI forums like CHI, TOCHI, CSCW, and CUI.
Thomas Mildner a postdoctoral researcher at the Digital Media Lab at the University of Bremen. His research focuses on ethical and responsible design and online wellbeing with studies exploring so-called dark patterns in social media as well as conversational technologies. To this end, Thomas collaborated to develop an ontology for dark patterns. His research is published in venues including CHI, DIS, and CUI.
Hans-Joachim Belz is a freelance user researcher and designer with over 30 years of experience designing, implementing, and managing digital products across various industries. From 2014 to 2024, he held a teaching position in ``Mobile Commerce'' at DHBW Mannheim (Baden-Wuerttemberg Cooperative State University). In 2020, his focus shifted to voice automation. In addition to his consultancy work in conversational AI, he employs Ethnomethodology and Conversation Analysis (EMCA) to study the expanding conversational capabilities of voice and multimodal user interfaces.
