Exploring Anthropomorphism in Conversational Agents for Environmental Sustainability

Abstract

The paper investigates the integration of Large Language Models (LLMs) into Conversational Agents (CAs) to encourage a shift in consumption patterns from a demand-driven to a supply-based paradigm. Specifically, the research examines the role of anthropomorphic design in delivering environmentally conscious messages by comparing two CA designs: a personified agent representing an appliance and a traditional, non-personified assistant. A lab study (N=26) assessed the impact of these designs on interaction, perceived self-efficacy, and engagement. Results indicate that LLM-based CAs significantly enhance users' self-reported eco-friendly behaviors, with participants expressing greater confidence in managing energy consumption. While the anthropomorphic design did not notably affect self-efficacy, those interacting with the personified agent reported a stronger sense of connection with the system. These findings suggest that although anthropomorphic CAs may improve user engagement, both designs hold promise for fostering sustainable behaviors in home energy management.