Author ORCID Identifier
https://orcid.org/0009-0000-6256-5523
Document Type
Conference Paper
Disciplines
Computer Sciences
Abstract
Conversational Agents have the potential to support healthcare through coaching exercise routines, but are still lacking in demonstrating authentic social behaviours to support engagement. To this end, we present a series of experiments that we conducted in order to investigate how automated health care coaches can be more effective when their interaction style is tailored to demonstrate qualities associated with a good bedside manner, namely active listening and reassurance. To test this, we first developed a dataset of 135 dialogue excerpts from three distinct sources, i.e., original, handcrafted and LLMs, the latter two of which were tuned to demonstrate specific types of comforting or reassuring language. Using this dataset, we conducted a study to validate whether users perceive different levels of active listening and reassurance across sources. The results of the study indicate that users can distinctly perceive the varying levels of stimuli across the three different data sources and that LLMs in particular clearly demonstrate these properties. In an accompanying analysis, the results showed that there is no notable influence of participant personality on perception, which we argue reduces the barrier to successful system deployment.
DOI
https://doi.org/10.5220/0013124900003911
Recommended Citation
HUSSAIN, GHULAM; Keegan, Brian; and Ross, Robert, "Quantifying the Role of Active Listening and Reassurance in Virtual Health Coach Interactions" (2025). Conference papers. 443.
https://arrow.tudublin.ie/scschcomcon/443
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Publication Details
https://www.scitepress.org/Link.aspx?doi=10.5220/0013124900003911
doi:10.5220/0013124900003911