拟人化对话 AI 头像能否促进可持续行为？白鲸头像的即时与长期效果实验

View PDF HTML (experimental)

Abstract:Embodied conversational AI can be persuasive, but can it motivate people to develop sustainable behavioral tendencies and increase pro-environmental attitudes? We conducted a randomized experiment (N = 576) comparing four embodied avatars--a beluga whale, Greta Thunberg, Emma Watson, and a generic human--with a text chatbot and no-intervention control. All embodied conditions increased immediate sustainable product selection relative to the control (beta = .401-.609, all q <= .0126) and chatbot (beta = .398-.604, all q <= .007), without differing significantly from one another. Only the Beluga condition increased immediate pro-environmental attitudes relative to the control after correction. Among 287 returners assessed two months later, following an intermediate assigned-condition session, Beluga also showed significantly higher pre-booster sustainable product choice compared to the control (beta = .657, q = .0176). Although it did not significantly outperform other embodied agents, these findings establish the immediate potential of nonhuman embodied avatar interfaces as a promising direction for memorable environmental interventions.

Subjects:	Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.33191 [cs.HC]
	(or arXiv:2610.33191v1 [cs.HC] for this version)
	https://doi.org/10.48550/arXiv.2610.33191 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Rachel Poonsiriwong [view email]
[v1] Fri, 23 Oct 2026 18:33:07 UTC (3,751 KB)