Chatbots With Attitude: Enhancing Chatbot Interactions Through Dynamic Personality Infusions

Jul 8, 2024·
N. Kovačević
,
T. Boschung
,
C. Holz
,
M. Gross
Dr. Rafael Wampfler
Dr. Rafael Wampfler
Abstract
We investigate dynamic personality infusion as a mechanism for enhancing user engagement in chatbot interactions. Rather than fixing a chatbot’s personality at design time, dynamic personality infusion allows the expressed personality to be modulated at inference time by conditioning language model generation on personality embeddings derived from the Big Five personality trait model. Through user studies comparing static and dynamically-personalized chatbots, we demonstrate that personality-adapted responses are perceived as more engaging, more natural, and more appropriate to context. We analyze which personality dimensions most strongly influence user satisfaction and provide design guidelines for personality-aware conversational AI.
Type
Publication
In Proceedings of the 6th International Conference on Conversational User Interfaces (CUI), Luxembourg
publications
Personality Chatbots Conversational AI User Engagement Large Language Models
Dr. Rafael Wampfler
Authors
Dr. Rafael Wampfler
Senior Researcher & Lecturer

I am a Senior Researcher & Lecturer at the Computer Graphics Laboratory of ETH Zurich, and a Research Consultant at Disney Research. I am leading the Digital Character AI projects at CGL. My research interests include conversational digital characters, affective computing, human-computer interaction, and applied machine learning.

My vision is to create intelligent digital humans that can naturally communicate, understand, and support people across domains such as education and mental health. My research focuses on multimodal artificial intelligence for interactive digital humans, developing models that combine large language models, affective computing, and data-driven animation to create embodied conversational agents endowed with autonomous agency, consistent values, and beliefs.

My work bridges machine learning, human–computer interaction, and computer graphics to enable AI systems such as Digital Einstein and interactive patient avatars for psychotherapy training and health education.