Metraipolis › archive › dc_55f3ca0be1ee
Persona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with Children — arXiv:2609.38782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:42:10.103Z
- SHA-256 of the archived text
7b9606a1d50b23be6a49c581f43b790016968ff6dce149ce30ff34f4d5b09f8a- Stable URL of this page
https://metraipolis.com/documento/dc_55f3ca0be1ee
How to cite
Persona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with Children — arXiv:2609.38782 — arXiv (en), https://arxiv.org/abs/2609.38782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55f3ca0be1ee (Metraipolis archive dc_55f3ca0be1ee, sha256 7b9606a1d50b23be6a49c581f43b790016968ff6dce149ce30ff34f4d5b09f8a)
BibTeX
@misc{dc55f3ca0be1ee,
title = {Persona and Persuasive Framing in AI Voice Agents: A $2times2$ Field Experiment with Children — arXiv:2609.38782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55f3ca0be1ee; sha256 7b9606a1d50b23be6a49c581f43b790016968ff6dce149ce30ff34f4d5b09f8a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Conversational agents increasingly interact with children, yet evidence on how their design shapes children's susceptibility to persuasion comes almost entirely from the lab. We report a $2\times2$ randomized field experiment embedded in a public German Santa Claus telephone hotline. Children's calls were randomly routed to one of four LLM voice agents varying persona (Santa, high authority, vs. Helper, low authority) and framing (persuasive nudges toward prosocial wishes vs. neutral). Of 1,072 logged calls, 89 conversations (median age 6) met inclusion criteria. Persuasive framing raised the probability of a prosocial wish from 11.6% to 45.7%, robust to controls. Persona authority showed a near-zero effect: Santa did not outperform the Helper. Persona instead shaped engagement; children hung up on the Helper far more often within the first minute (65% vs. 39%). Where context already lends an agent legitimacy, how it speaks shapes children's compliance more than who it claims to be. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.38782 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:14:13.683Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).