Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carrillo, Alexis, Taietta, Enrique, Ardebili, Ali Aghazadeh, Veltri, Giuseppe Alessandro, Stella, Massimo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914447972368384
author Carrillo, Alexis
Taietta, Enrique
Ardebili, Ali Aghazadeh
Veltri, Giuseppe Alessandro
Stella, Massimo
author_facet Carrillo, Alexis
Taietta, Enrique
Ardebili, Ali Aghazadeh
Veltri, Giuseppe Alessandro
Stella, Massimo
contents Talk2AI is a large-scale longitudinal dataset of 3,080 conversations (totaling 30,800 turns) between human participants and Large Language Models (LLMs), designed to support research on persuasion, opinion change, and human-AI interaction. The corpus was collected from 770 profiled Italian adults across four weekly sessions in Spring 2025, using a within-subject design in which each participant conversed with a single model (GPT-4o, Claude Sonnet 3.7, DeepSeek-chat V3, or Mistral Large) on three socially relevant topics: climate change, math anxiety, and health misinformation. Each conversation is linked to rich contextual data, including sociodemographic characteristics and psychometric profiles. After each session, participants reported on opinion change, conviction stability, perceived humanness of the AI, and behavioral intentions, enabling fine-grained longitudinal analysis of how AI-mediated dialogue shapes beliefs and attitudes over time.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations
Carrillo, Alexis
Taietta, Enrique
Ardebili, Ali Aghazadeh
Veltri, Giuseppe Alessandro
Stella, Massimo
Human-Computer Interaction
Computation and Language
Computers and Society
H.5.2; I.2.7; J.4; H.1.2
Talk2AI is a large-scale longitudinal dataset of 3,080 conversations (totaling 30,800 turns) between human participants and Large Language Models (LLMs), designed to support research on persuasion, opinion change, and human-AI interaction. The corpus was collected from 770 profiled Italian adults across four weekly sessions in Spring 2025, using a within-subject design in which each participant conversed with a single model (GPT-4o, Claude Sonnet 3.7, DeepSeek-chat V3, or Mistral Large) on three socially relevant topics: climate change, math anxiety, and health misinformation. Each conversation is linked to rich contextual data, including sociodemographic characteristics and psychometric profiles. After each session, participants reported on opinion change, conviction stability, perceived humanness of the AI, and behavioral intentions, enabling fine-grained longitudinal analysis of how AI-mediated dialogue shapes beliefs and attitudes over time.
title Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations
topic Human-Computer Interaction
Computation and Language
Computers and Society
H.5.2; I.2.7; J.4; H.1.2
url https://arxiv.org/abs/2604.04354