A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media

Online social networks (OSNs) play an integral role in facilitating social interaction; however, these social networks increase antisocial behavior, such as cyberbullying, hate speech, and trolling. Aggression or hate speech that takes place through short message service (SMS) or the Internet (e.g.,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Munif Alotaibi, Bandar Alotaibi, Abdul Razaque
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Online social networks (OSNs) sentiment analysis cyberbullying natural language processing (NLP) neural networks Twitter Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/14deff3c56fc4acca350c4921838b59d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:14deff3c56fc4acca350c4921838b59d
record_format	dspace
spelling	oai:doaj.org-article:14deff3c56fc4acca350c4921838b59d2021-11-11T15:39:40ZA Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media10.3390/electronics102126642079-9292https://doaj.org/article/14deff3c56fc4acca350c4921838b59d2021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2664https://doaj.org/toc/2079-9292Online social networks (OSNs) play an integral role in facilitating social interaction; however, these social networks increase antisocial behavior, such as cyberbullying, hate speech, and trolling. Aggression or hate speech that takes place through short message service (SMS) or the Internet (e.g., in social media platforms) is known as cyberbullying. Therefore, automatic detection utilizing natural language processing (NLP) is a necessary first step that helps prevent cyberbullying. This research proposes an automatic cyberbullying method to detect aggressive behavior using a consolidated deep learning model. This technique utilizes multichannel deep learning based on three models, namely, the bidirectional gated recurrent unit (BiGRU), transformer block, and convolutional neural network (CNN), to classify Twitter comments into two categories: aggressive and not aggressive. Three well-known hate speech datasets were combined to evaluate the performance of the proposed method. The proposed method achieved promising results. The accuracy of the proposed method was approximately 88%.Munif AlotaibiBandar AlotaibiAbdul RazaqueMDPI AGarticleOnline social networks (OSNs)sentiment analysiscyberbullying natural language processing (NLP)neural networksTwitterElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2664, p 2664 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Online social networks (OSNs) sentiment analysis cyberbullying natural language processing (NLP) neural networks Twitter Electronics TK7800-8360
spellingShingle	Online social networks (OSNs) sentiment analysis cyberbullying natural language processing (NLP) neural networks Twitter Electronics TK7800-8360 Munif Alotaibi Bandar Alotaibi Abdul Razaque A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
description	Online social networks (OSNs) play an integral role in facilitating social interaction; however, these social networks increase antisocial behavior, such as cyberbullying, hate speech, and trolling. Aggression or hate speech that takes place through short message service (SMS) or the Internet (e.g., in social media platforms) is known as cyberbullying. Therefore, automatic detection utilizing natural language processing (NLP) is a necessary first step that helps prevent cyberbullying. This research proposes an automatic cyberbullying method to detect aggressive behavior using a consolidated deep learning model. This technique utilizes multichannel deep learning based on three models, namely, the bidirectional gated recurrent unit (BiGRU), transformer block, and convolutional neural network (CNN), to classify Twitter comments into two categories: aggressive and not aggressive. Three well-known hate speech datasets were combined to evaluate the performance of the proposed method. The proposed method achieved promising results. The accuracy of the proposed method was approximately 88%.
format	article
author	Munif Alotaibi Bandar Alotaibi Abdul Razaque
author_facet	Munif Alotaibi Bandar Alotaibi Abdul Razaque
author_sort	Munif Alotaibi
title	A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
title_short	A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
title_full	A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
title_fullStr	A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
title_full_unstemmed	A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media
title_sort	multichannel deep learning framework for cyberbullying detection on social media
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/14deff3c56fc4acca350c4921838b59d
work_keys_str_mv	AT munifalotaibi amultichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia AT bandaralotaibi amultichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia AT abdulrazaque amultichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia AT munifalotaibi multichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia AT bandaralotaibi multichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia AT abdulrazaque multichanneldeeplearningframeworkforcyberbullyingdetectiononsocialmedia
_version_	1718434521550946304

A Multichannel Deep Learning Framework for Cyberbullying Detection on Social Media

Ejemplares similares