Informing Robot Wellbeing Coach Design through Longitudinal Analysis of Human-AI Dialogue

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shah, Keya, Lalwani, Himanshi, Mukhanov, Zein, Salam, Hanan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908812801212416
author Shah, Keya
Lalwani, Himanshi
Mukhanov, Zein
Salam, Hanan
author_facet Shah, Keya
Lalwani, Himanshi
Mukhanov, Zein
Salam, Hanan
contents Social robots and conversational agents are being explored as supports for wellbeing, goal-setting, and everyday self-regulation. While prior work highlights their potential to motivate and guide users, much of the evidence relies on self-reported outcomes or short, researcher-mediated encounters. As a result, we know little about the interaction dynamics that unfold when people use such systems in real-world contexts, and how these dynamics should shape future robot wellbeing coaches. This paper addresses this gap through content analysis of 4352 messages exchanged longitudinally between 38 university students and an LLM-based wellbeing coach. Our results provide a fine-grained view into how users naturally shape, steer, and sometimes struggle within supportive human-AI dialogue, revealing patterns of user-led direction, guidance-seeking, and emotional expression. We discuss how these dynamics can inform the design of robot wellbeing coaches that support user autonomy, provide appropriate scaffolding, and uphold ethical boundaries in sustained wellbeing interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04478
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Informing Robot Wellbeing Coach Design through Longitudinal Analysis of Human-AI Dialogue
Shah, Keya
Lalwani, Himanshi
Mukhanov, Zein
Salam, Hanan
Human-Computer Interaction
Social robots and conversational agents are being explored as supports for wellbeing, goal-setting, and everyday self-regulation. While prior work highlights their potential to motivate and guide users, much of the evidence relies on self-reported outcomes or short, researcher-mediated encounters. As a result, we know little about the interaction dynamics that unfold when people use such systems in real-world contexts, and how these dynamics should shape future robot wellbeing coaches. This paper addresses this gap through content analysis of 4352 messages exchanged longitudinally between 38 university students and an LLM-based wellbeing coach. Our results provide a fine-grained view into how users naturally shape, steer, and sometimes struggle within supportive human-AI dialogue, revealing patterns of user-led direction, guidance-seeking, and emotional expression. We discuss how these dynamics can inform the design of robot wellbeing coaches that support user autonomy, provide appropriate scaffolding, and uphold ethical boundaries in sustained wellbeing interactions.
title Informing Robot Wellbeing Coach Design through Longitudinal Analysis of Human-AI Dialogue
topic Human-Computer Interaction
url https://arxiv.org/abs/2602.04478