Digital health interventions often rely on static message templates for health behaviour support, which can struggle to sustain engagement over time. Large language models (LLMs) offer a promising alternative by enabling context-sensitive message generation with personality-trait-based language adaptation across repeated interactions. Yet most prior work evaluates generated messages in isolation, leaving unclear whether such adaptation improves perceptions of individual messages or whether its benefits emerge through cumulative exposure. To examine this question, 90 participants rated hypothetical messages generated with four LLM strategies, with and without Big Five personality-trait-based language adaptation, in a controlled online study. Using ordinal multilevel models with within-person and between-person decomposition, we found no message-level effect on perceived personalisation. However, greater exposure to personality-trait-adapted messages was associated with increased perceived personalisation, increased appropriateness, and decreased negative affect. These findings suggest that the benefits of personality-trait-based language adaptation may emerge through sustained interaction rather than single-message optimisation.
Dominik P. Hofer, David Haag, R. Islambouli et al.· Message Understanding Confer...· 0 citations
Adaptive digital health systems increasingly rely on artificial intelligence to deliver Just-in-Time Adaptive Interventions (JITAIs), providing health behavioral support based on real-time contextual information. While substantial research has focused on sensing technologies and algorithmic optimization, far less attention has been given to how these systems communicate with users during sensitive or context-dependent moments. In particular, the interactional qualities of AI-generated health messages remain underexplored. This Birds of a Feather (BoF) session brings together researchers and practitioners from Interactive Health, Human–Computer Interaction, behavioral science, and artificial intelligence to explore what constitutes high-quality AI communication in adaptive health interventions. Through facilitated discussion and small-group activities, participants will analyze example AI-generated messages and reflect on how communication influences user perception and response. The session aims to surface key challenges, share perspectives across disciplines, and foster an interdisciplinary community interested in advancing interactional quality in AI-mediated health communication.
Rania Islambouli, David Haag, F. Young· Information Hiding· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
