Exploring Anthropomorphism in Conversational Agents for Environmental Sustainability
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909676672647168 |
|---|---|
| author | Giudici, Mathyas Scherini, Samuele Chaussumier, Pascal Ginocchio, Stefano Garzotto, Franca |
| author_facet | Giudici, Mathyas Scherini, Samuele Chaussumier, Pascal Ginocchio, Stefano Garzotto, Franca |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Anthropomorphism in Conversational Agents for Environmental Sustainability Giudici, Mathyas Scherini, Samuele Chaussumier, Pascal Ginocchio, Stefano Garzotto, Franca Human-Computer Interaction 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. |
| title | Exploring Anthropomorphism in Conversational Agents for Environmental Sustainability |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2505.07142 |