![[2602.12924] Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.12924] Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues
Summary
This article examines how the availability of knowledge influences the persuasiveness of generative social agents (GSAs) in physiotherapy dialogues, highlighting the importance of contextual information in enhancing motivational communication.
Why It Matters
As generative AI systems like ChatGPT are increasingly used in health-related contexts, understanding their persuasive capabilities is crucial for ensuring effective and ethical interactions. This research provides insights into how knowledge availability can enhance or hinder agent effectiveness, informing future designs of AI in healthcare.
Key Takeaways
- Generative social agents can adapt their persuasive traits based on available knowledge.
- Specific contextual information, such as a patient's age and profession, significantly enhances perceived persuasiveness.
- Empirical studies on GSA behavior are essential for responsible AI communication in health contexts.
Computer Science > Human-Computer Interaction arXiv:2602.12924 (cs) [Submitted on 13 Feb 2026] Title:Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues Authors:Stephan Vonschallen, Rahel Häusler, Theresa Schmiedel, Friederike Eyssel View a PDF of the paper titled Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialogues, by Stephan Vonschallen and 3 other authors View PDF HTML (experimental) Abstract:Generative Social Agents (GSAs) are increasingly impacting human users through persuasive means. On the one hand, they might motivate users to pursue personal goals, such as healthier lifestyles. On the other hand, they are associated with potential risks like manipulation and deception, which are induced by limited control over probabilistic agent outputs. However, as GSAs manifest communicative patterns based on available knowledge, their behavior may be regulated through their access to such knowledge. Following this approach, we explored persuasive ChatGPT-generated messages in the context of human-robot physiotherapy motivation. We did so by comparing ChatGPT-generated responses to predefined inputs from a hypothetical physiotherapy patient. In Study 1, we qualitatively analyzed 13 ChatGPT-generated dialogue scripts with varying knowledge configurations regarding persuasive message characteristics. In Study 2, thi...