Descripción:
Although companion virtual agents (CVAs) are increasingly adopted to support well-being, interaction patterns between adults and CVAs remain underexplored. This study examines how users engage with CVAs over time, exploring conversation patterns, interaction frequency, attitudes, and emotional responses over a seven-day period. Twenty-four adults engaged with a GPT-4-powered embodied CVA daily, discussing topics from personal interests to emotional reflections. Quantitative measures, including loneliness and affect scales, revealed no significant reduction in loneliness but noted decreases in positive affect and nervousness. Qualitative analysis highlighted evolving conversational dynamics, with participants shifting from exploratory questions to more reflective and personal discussions. Participants appreciated the agent’s ability to engage in fluid and meaningful conversations. However, participants also noted shortcomings, including limited recall and occasional conversational unnaturalness. These findings inform the design of CVAs, emphasizing the need for adaptive conversational strategies, enhanced emotional responsiveness, and improved memory systems to foster meaningful connections.
Tipo de publicación: Conference Paper
Publicado en: Proceedings of the 13th International Conference on Human-Agent Interaction
Autores- Calvo, Rodrigo
- Wang, Heting
- Barquero, Alexander
- Zhang, Xuanpu
- Venkatakrishnan, Rohith
- Ruiz, Jaime
Investigadores del CITIC asociados a la publicación
Dr. Alexander Barquero Elizondo
Proyecto asociado a la publicación
Evaluación de la interacción humana con agentes virtuales en el contexto costarricense