Joel Wester – Ph.D. Fellow

Joel Wester, PhD Fellow
Human-Computer Interaction
Human-Centered Artificial Intelligence

About

My name is Joel, and I am a PhD Fellow in the Human Centered Computing research group. With a background in cognitive science, psychology, and philosophy, I bring a multifaceted viewpoint to human-AI interactions.

I’m primarily interested in enhancing how people interact with AI-powered systems, with a special emphasis on human-LLM interactions. I aim to better understand how these systems can support users more effectively. By integrating insights from various disciplines, I work to create interactions that are both meaningful and tailored to the unique needs of each individual.

Publications

Wester, J., Schrills, T., Pohl, H., van Berkel, N. (2024). “As an AI language model, I cannot”: Investigating LLM Denials of User Requests, in Proceedings of ACM SIGCHI Conference on Human Factors in Computing Systems (CHI’24).
Paper, 🏆 Best Paper Honorable Mention Award

Wester, J., Moghe, B., Winkle, K., van Berkel, N. (2024). Facing LLMs: Robot Communication Styles in Mediating Health Information between Parents and Young Adults, in Proceedings of the ACM on Human-Computer Interaction (CSCW).
To appear

Wester, J., Pohl, H., Hosio, S., van Berkel, N. (2024). “This Chatbot Would Never…”: Perceived Moral Agency of Mental Health Chatbots, in Proceedings of the ACM on Human-Computer Interaction, vol. 8, no. CSCW1.
Paper

Wester, J., de Jong, S., Pohl, H., van Berkel, N. (2024). Exploring People’s Perceptions of LLM-generated Advice, in Computers in Human Behavior: Artificial Humans.
Paper

Kollerup, N.K., Wester, J., Skov, M.B., van Berkel, N. (2024). How Can I Signal You To Trust Me: Investigating AI Trust Signalling in Clinical Self-Assessments, in Proceedings of the ACM SIGCHI Conference on Designing Interactive Systems (DIS’24).
Paper

Brännström, A., Wester, J., Nieves, JC. (2024). A formal understanding of computational empathy in interactive agents, in Cognitive Systems Research, 2024.
Paper

Wester, J., Brännström, A., Nieves, JC., van Berkel, N., (2023). “You’ve Got a Friend in Me”: A Formal Understanding of the Critical Friend Agent, in Proceedings of the 11th International Conference on Human-Agent Interaction, 2023. (HAI’23 EA)
Paper

Wester, J., Lee, M., van Berkel, N., (2023). Moral Transparency as a Mitigator of Moral Bias in Conversational User Interfaces, in Proceedings of the 5th International Conference on Conversational User Interfaces, 2023. (CUI’23 EA)
Paper

Adjunct Proceedings

Wester, J., Møberg Jacobsen, R., de Jong, S., Kathrine Kollerup, N., Bøjer Djernæs, H., van Berkel, N. (2024). Theory of Mind and Self-Presentation in Human-LLM Interactions, in Adjunct Proceedings of ACM SIGCHI Conference on Human Factors in Computing Systems (CHI’24 WS).
Paper

Wester, J., Delaunay, J., de Jong, S., van Berkel, N., (2023). On Moral Manifestations in Large Language Models, in Adjunct Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI’23 WS)
Paper

van Berkel, N., de Jong, S., Wester, J., Als, N. K. K. (2023). The Challenge of Bias Mitigation in Clinical AI Decision Support: A Balance Between Decision Efficiency and Quality, In Adjunct Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI’23 WS).
Paper

Wester, J., Schneiders, E., & van Berkel, N. (2023). Perceived Moral Agency of Non-Moral Entities: Implications and Future Research Directions for Social Robots, In Adjunct Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI’23 WS).
Paper

Wester, J., Brännström, A., & Nieves, J. C. (2022). Towards a Formalization of the Critical Friend and Socio-Moral Decision-Making in Autonomous Systems, In Adjunct Proceedings of the International Joint Conference on Artificial Intelligence and the European Conference on Artificial Intelligence (IJCAI-ECAI’22 WS)
Paper