Simulating conversations on social media with generative agent-based models

Simple item page
dc.article.number79
dc.catalogadorgjm
dc.contributor.authorJeon, Min Soo
dc.contributor.authorMendoza Rocha, Marcelo
dc.contributor.authorFernández Pizarro, Miguel
dc.contributor.authorProvidel, Eliana
dc.contributor.authorRodríguez Bórquez, Felipe
dc.contributor.authorEspina Quilodrán, Nicolás Gonzalo
dc.contributor.authorCarvallo, Andrés
dc.contributor.authorAbeliuk, Andrés
dc.date.accessioned2025-12-09T15:32:55Z
dc.date.available2025-12-09T15:32:55Z
dc.date.issued2025
dc.date.updated2025-11-16T01:04:53Z
dc.description.abstractLarge Language Models (LLMs) can generate realistic text resembling human-produced content. However, the ability of these models to simulate conversations on social media is still less explored. To investigate the potential and limitations of simulated text in this domain, we introduce network-simulator, a system to simulate conversations on social media. First, we simulate the macro structure of a conversation using Agent-Based Modeling (ABM). The generated structure defines who interacts with whom, the type of interaction, and the agent’s stance on the topic of the conversation. Subsequently, using the simulated interaction structure, our system generates prompts conditioned on the simulation variables, producing texts that are conditioned on the parameters of the predefined structure, guiding a micro simulation process. We compare human conversations with those simulated by our system. Based on stylistic and model-based metrics, we found that our system can simulate conversations on social media in various dimensions. However, we detected differences in metrics related to the predictability of text production. Furthermore, we examine the effect of true and false framings within simulated conversations, revealing that simulated discussions surrounding false information exhibit a more negative collective sentiment bias than those based on true content.
dc.fechaingreso.objetodigital2025-12-09
dc.format.extent22 páginas
dc.fuente.origenAutoarchivo
dc.identifier.citationEPJ Data Science. 2025 Nov 11;14(1):79
dc.identifier.urihttps://doi.org/10.1140/epjds/s13688-025-00593-3
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/107313
dc.information.autorucEscuela de Ingeniería; Jeon, Min Soo; S/I; 1133310
dc.information.autorucEscuela de Ingeniería; Mendoza Rocha, Marcelo; 0000-0002-7969-6041; 1237020
dc.information.autorucEscuela de Ingeniería; Rodríguez Bórquez, Felipe; S/I; 1064943
dc.information.autorucEscuela de Ingeniería; Espina Quilodrán, Nicolás Gonzalo; S/I; 244608
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaEPJ Data Science
dc.rightsacceso abierto
dc.rights.holderThe Author(s)
dc.rights.licenseCC BY-NC-ND 4.0 Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectLarge language Models
dc.subjectAgent-based Modeling
dc.subjectOnline Conversations
dc.titleSimulating conversations on social media with generative agent-based models
dc.typeartículo
dc.volumen14
sipa.codpersvinculados1133310
sipa.codpersvinculados1237020
sipa.codpersvinculados1064943
sipa.codpersvinculados244608
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
13688_2025_Article_593.pdf
Size:
2.48 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas