A comparative analysis of machine learning techniques for cyberbullying detection on twitter

The advent of social media, particularly Twitter, raises many issues due to a misunderstanding regarding the concept of freedom of speech. One of these issues is cyberbullying, which is a critical global issue that affects both individual victims and societies. Many attempts have been introduced in...

Full description

Saved in:
Bibliographic Details
Main Authors: Muneer, A., Fati, S.M.
Format: Article
Published: MDPI AG 2020
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094647882&doi=10.3390%2ffi12110187&partnerID=40&md5=acfb2035f75c97ceb36c1ef6c292b2c8
http://eprints.utp.edu.my/29810/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknologi Petronas
id my.utp.eprints.29810
record_format eprints
spelling my.utp.eprints.298102022-03-25T02:56:45Z A comparative analysis of machine learning techniques for cyberbullying detection on twitter Muneer, A. Fati, S.M. The advent of social media, particularly Twitter, raises many issues due to a misunderstanding regarding the concept of freedom of speech. One of these issues is cyberbullying, which is a critical global issue that affects both individual victims and societies. Many attempts have been introduced in the literature to intervene in, prevent, or mitigate cyberbullying; however, because these attempts rely on the victims� interactions, they are not practical. Therefore, detection of cyberbullying without the involvement of the victims is necessary. In this study, we attempted to explore this issue by compiling a global dataset of 37,373 unique tweets from Twitter. Moreover, seven machine learning classifiers were used, namely, Logistic Regression (LR), Light Gradient Boosting Machine (LGBM), Stochastic Gradient Descent (SGD), Random Forest (RF), AdaBoost (ADB), Naive Bayes (NB), and Support Vector Machine (SVM). Each of these algorithms was evaluated using accuracy, precision, recall, and F1 score as the performance metrics to determine the classifiers� recognition rates applied to the global dataset. The experimental results show the superiority of LR, which achieved a median accuracy of around 90.57. Among the classifiers, logistic regression achieved the best F1 score (0.928), SGD achieved the best precision (0.968), and SVM achieved the best recall (1.00). © 2020 by the authors. Licensee MDPI, Basel, Switzerland. MDPI AG 2020 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094647882&doi=10.3390%2ffi12110187&partnerID=40&md5=acfb2035f75c97ceb36c1ef6c292b2c8 Muneer, A. and Fati, S.M. (2020) A comparative analysis of machine learning techniques for cyberbullying detection on twitter. Future Internet, 12 (11). pp. 1-21. http://eprints.utp.edu.my/29810/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description The advent of social media, particularly Twitter, raises many issues due to a misunderstanding regarding the concept of freedom of speech. One of these issues is cyberbullying, which is a critical global issue that affects both individual victims and societies. Many attempts have been introduced in the literature to intervene in, prevent, or mitigate cyberbullying; however, because these attempts rely on the victims� interactions, they are not practical. Therefore, detection of cyberbullying without the involvement of the victims is necessary. In this study, we attempted to explore this issue by compiling a global dataset of 37,373 unique tweets from Twitter. Moreover, seven machine learning classifiers were used, namely, Logistic Regression (LR), Light Gradient Boosting Machine (LGBM), Stochastic Gradient Descent (SGD), Random Forest (RF), AdaBoost (ADB), Naive Bayes (NB), and Support Vector Machine (SVM). Each of these algorithms was evaluated using accuracy, precision, recall, and F1 score as the performance metrics to determine the classifiers� recognition rates applied to the global dataset. The experimental results show the superiority of LR, which achieved a median accuracy of around 90.57. Among the classifiers, logistic regression achieved the best F1 score (0.928), SGD achieved the best precision (0.968), and SVM achieved the best recall (1.00). © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
format Article
author Muneer, A.
Fati, S.M.
spellingShingle Muneer, A.
Fati, S.M.
A comparative analysis of machine learning techniques for cyberbullying detection on twitter
author_facet Muneer, A.
Fati, S.M.
author_sort Muneer, A.
title A comparative analysis of machine learning techniques for cyberbullying detection on twitter
title_short A comparative analysis of machine learning techniques for cyberbullying detection on twitter
title_full A comparative analysis of machine learning techniques for cyberbullying detection on twitter
title_fullStr A comparative analysis of machine learning techniques for cyberbullying detection on twitter
title_full_unstemmed A comparative analysis of machine learning techniques for cyberbullying detection on twitter
title_sort comparative analysis of machine learning techniques for cyberbullying detection on twitter
publisher MDPI AG
publishDate 2020
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094647882&doi=10.3390%2ffi12110187&partnerID=40&md5=acfb2035f75c97ceb36c1ef6c292b2c8
http://eprints.utp.edu.my/29810/
_version_ 1738657018676248576