A normative approach to radicalization in social networks

Bouttier, Vincent; Leclercq, Salome; Jardri, Renaud; Denève, Sophie

Type de document :

Article dans une revue scientifique: Article original

DOI :

10.1007/s42001-024-00267-6

URL permanente :

http://hdl.handle.net/20.500.12210/114217

Titre :

A normative approach to radicalization in social networks

Auteur(s) :

Bouttier, Vincent [Auteur]
Laboratoire de Neurosciences Cognitives & Computationnelles [LNC2]
Leclercq, Salome [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Jardri, Renaud [Auteur]

Lille Neurosciences & Cognition (LilNCog) - U 1172
Denève, Sophie [Auteur]
Laboratoire de Neurosciences Cognitives & Computationnelles [LNC2]

Titre de la revue :

Journal of Computational Social Science

Nom court de la revue :

J. Comput. Soc. Sci.

Numéro :

Pagination :

Date de publication :

2024-04-10

ISSN :

2432-2717

Mot(s)-clé(s) en anglais :

Bayes
Belief
Circular
Inference
Radicalization
Polarization

Discipline(s) HAL :

Sciences du Vivant [q-bio]

Résumé en anglais : [en]

In recent decades, the massification of online social connections has made information globally accessible in a matter of seconds. Unfortunately, this has been accompanied by a dramatic surge in extreme opinions, without ...
Lire la suite >In recent decades, the massification of online social connections has made information globally accessible in a matter of seconds. Unfortunately, this has been accompanied by a dramatic surge in extreme opinions, without a clear solution in sight. Using a model performing probabilistic inference in large-scale loopy graphs through exchange of messages between nodes, we show how circularity in the social graph directly leads to radicalization and the polarization of opinions. We demonstrate that these detrimental effects could be avoided if the correlations between incoming messages could be decreased. This approach is based on an extension of Belief Propagation (BP) named Circular Belief Propagation (CBP) that can be trained to drastically improve inference within a cyclic graph. CBP was benchmarked using data from Facebook© and Twitter©. This approach could inspire new methods for preventing the viral spreading and amplification of misinformation online, improving the capacity of social networks to share knowledge globally without resorting to censorship.Lire moins >

Langue :

Anglais

Audience :

Internationale

Vulgarisation :

Non

Établissement(s) :

Université de Lille
Inserm
CHU Lille

Collections :

Lille Neurosciences & Cognition (LilNCog) - U 1172

Date de dépôt :

2024-05-06T23:15:16Z
2024-06-10T10:51:57Z

Fichiers

s42001-024-00267-6.pdf
Non spécifié
Accès libre
Accéder au document

Ce document est diffusé sous licence Attribution 3.0 United States

Numéro de version	Lien	Date de modification
2	20.500.12210/114217*	2024-06-10T10:38:56Z
1	20.500.12210/114217.1	2024-05-06T23:15:16Z

A normative approach to radicalization in ...

BibTeX

CSV

Excel

RIS

Fichiers

Historique des modifications

A normative approach to radicalization in ... BibTeX CSV Excel RIS

Fichiers

Historique des modifications

A normative approach to radicalization in ...

BibTeX

CSV

Excel

RIS