Artificial personality model improves user satisfaction with chatbots
The Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents
Human-Computer InteractionArtificial Intelligence
Summary
People often interact with chatbots and virtual assistants, but making these conversations feel natural and enjoyable can be tricky. The authors created and tested a new model called the Artificial Personality Model to help design chatbot personalities that users find more satisfying and engaging. They found that some human personality traits can be represented in chatbots, while others do not clearly appear. Their new questionnaire helps measure how users perceive a chatbot’s personality and shows that personality affects how much users like and want to keep using these chatbots.
What this means in practice
- •For chatbot developers: Design chatbot personalities that enhance user satisfaction and encourage ongoing interaction using the Artificial Personality Model and its questionnaire.
- •For customer service platform teams: Improve user engagement and social presence in automated customer support by integrating validated artificial personality traits into conversational agents.
Authors
Alexander Dregger, Barbarella Petz, Erik Kuhn, Pia Volk, Andreas Oberweis, Stefan Hillmann, Jannik Strötgen
Abstract
Artificial personality shapes user experience (UX) in human-machine interaction, yet coherent theoretical frameworks and validated measurement instruments remain limited. This paper refines and empirically evaluates the Artificial Personality Model (APM), a hybrid framework integrating human-centred and machine-specific personality dimensions. Across three experiments (N = 395), the model was operationalised and evaluated using the Artificial Personality Questionnaire (APQ). Factor analyses revealed that some human personality dimensions (e.g., agreeableness, conscientiousness) are partially transferable, whereas others (e.g., extraversion) did not emerge as distinct dimensions. Additional machine-specific dimensions were identified. The APQ provided encouraging initial psychometric evidence, while the human-centred BFI-2 showed poor reliability and an uninterpretable factor structure in Experiment 3. Experimental manipulations demonstrated significant effects of artificial personality on user satisfaction, continuous use intention, and social presence. The findings contribute an empirically refined framework and a novel instrument for measuring perceived artificial personality, offering practical guidance for designing conversational agents.