Dynamics of online hate and misinformation

Abstract Online debates are often characterised by extreme polarisation and heated discussions among users. The presence of hate speech online is becoming increasingly problematic, making necessary the development of appropriate countermeasures. In this work, we perform hate speech detection on a co...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Matteo Cinelli, Andraž Pelicon, Igor Mozetič, Walter Quattrociocchi, Petra Kralj Novak, Fabiana Zollo
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ed8256497a1b4f2ca0646267f13994e7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ed8256497a1b4f2ca0646267f13994e7
record_format dspace
spelling oai:doaj.org-article:ed8256497a1b4f2ca0646267f13994e72021-11-14T12:24:19ZDynamics of online hate and misinformation10.1038/s41598-021-01487-w2045-2322https://doaj.org/article/ed8256497a1b4f2ca0646267f13994e72021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01487-whttps://doaj.org/toc/2045-2322Abstract Online debates are often characterised by extreme polarisation and heated discussions among users. The presence of hate speech online is becoming increasingly problematic, making necessary the development of appropriate countermeasures. In this work, we perform hate speech detection on a corpus of more than one million comments on YouTube videos through a machine learning model, trained and fine-tuned on a large set of hand-annotated data. Our analysis shows that there is no evidence of the presence of “pure haters”, meant as active users posting exclusively hateful comments. Moreover, coherently with the echo chamber hypothesis, we find that users skewed towards one of the two categories of video channels (questionable, reliable) are more prone to use inappropriate, violent, or hateful language within their opponents’ community. Interestingly, users loyal to reliable sources use on average a more toxic language than their counterpart. Finally, we find that the overall toxicity of the discussion increases with its length, measured both in terms of the number of comments and time. Our results show that, coherently with Godwin’s law, online debates tend to degenerate towards increasingly toxic exchanges of views.Matteo CinelliAndraž PeliconIgor MozetičWalter QuattrociocchiPetra Kralj NovakFabiana ZolloNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Matteo Cinelli
Andraž Pelicon
Igor Mozetič
Walter Quattrociocchi
Petra Kralj Novak
Fabiana Zollo
Dynamics of online hate and misinformation
description Abstract Online debates are often characterised by extreme polarisation and heated discussions among users. The presence of hate speech online is becoming increasingly problematic, making necessary the development of appropriate countermeasures. In this work, we perform hate speech detection on a corpus of more than one million comments on YouTube videos through a machine learning model, trained and fine-tuned on a large set of hand-annotated data. Our analysis shows that there is no evidence of the presence of “pure haters”, meant as active users posting exclusively hateful comments. Moreover, coherently with the echo chamber hypothesis, we find that users skewed towards one of the two categories of video channels (questionable, reliable) are more prone to use inappropriate, violent, or hateful language within their opponents’ community. Interestingly, users loyal to reliable sources use on average a more toxic language than their counterpart. Finally, we find that the overall toxicity of the discussion increases with its length, measured both in terms of the number of comments and time. Our results show that, coherently with Godwin’s law, online debates tend to degenerate towards increasingly toxic exchanges of views.
format article
author Matteo Cinelli
Andraž Pelicon
Igor Mozetič
Walter Quattrociocchi
Petra Kralj Novak
Fabiana Zollo
author_facet Matteo Cinelli
Andraž Pelicon
Igor Mozetič
Walter Quattrociocchi
Petra Kralj Novak
Fabiana Zollo
author_sort Matteo Cinelli
title Dynamics of online hate and misinformation
title_short Dynamics of online hate and misinformation
title_full Dynamics of online hate and misinformation
title_fullStr Dynamics of online hate and misinformation
title_full_unstemmed Dynamics of online hate and misinformation
title_sort dynamics of online hate and misinformation
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/ed8256497a1b4f2ca0646267f13994e7
work_keys_str_mv AT matteocinelli dynamicsofonlinehateandmisinformation
AT andrazpelicon dynamicsofonlinehateandmisinformation
AT igormozetic dynamicsofonlinehateandmisinformation
AT walterquattrociocchi dynamicsofonlinehateandmisinformation
AT petrakraljnovak dynamicsofonlinehateandmisinformation
AT fabianazollo dynamicsofonlinehateandmisinformation
_version_ 1718429262922383360