Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques
The rise in web and social media interactions has resulted in the efortless proliferation of offensive language and hate speech. Such online harassment, insults, and attacks are commonly termed cyberbullying. The sheer volume of user-generated content has made it challenging to identify such illicit...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/22/2810 |
_version_ | 1797510535065894912 |
---|---|
author | Chahat Raj Ayush Agarwal Gnana Bharathy Bhuva Narayan Mukesh Prasad |
author_facet | Chahat Raj Ayush Agarwal Gnana Bharathy Bhuva Narayan Mukesh Prasad |
author_sort | Chahat Raj |
collection | DOAJ |
description | The rise in web and social media interactions has resulted in the efortless proliferation of offensive language and hate speech. Such online harassment, insults, and attacks are commonly termed cyberbullying. The sheer volume of user-generated content has made it challenging to identify such illicit content. Machine learning has wide applications in text classification, and researchers are shifting towards using deep neural networks in detecting cyberbullying due to the several advantages they have over traditional machine learning algorithms. This paper proposes a novel neural network framework with parameter optimization and an algorithmic comparative study of eleven classification methods: four traditional machine learning and seven shallow neural networks on two real world cyberbullying datasets. In addition, this paper also examines the effect of feature extraction and word-embedding-techniques-based natural language processing on algorithmic performance. Key observations from this study show that bidirectional neural networks and attention models provide high classification results. Logistic Regression was observed to be the best among the traditional machine learning classifiers used. Term Frequency-Inverse Document Frequency (TF-IDF) demonstrates consistently high accuracies with traditional machine learning techniques. Global Vectors (GloVe) perform better with neural network models. Bi-GRU and Bi-LSTM worked best amongst the neural networks used. The extensive experiments performed on the two datasets establish the importance of this work by comparing eleven classification methods and seven feature extraction techniques. Our proposed shallow neural networks outperform existing state-of-the-art approaches for cyberbullying detection, with accuracy and F1-scores as high as ~95% and ~98%, respectively. |
first_indexed | 2024-03-10T05:33:35Z |
format | Article |
id | doaj.art-b7ac124425df485898e1232de3eb6bf3 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T05:33:35Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-b7ac124425df485898e1232de3eb6bf32023-11-22T23:07:26ZengMDPI AGElectronics2079-92922021-11-011022281010.3390/electronics10222810Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing TechniquesChahat Raj0Ayush Agarwal1Gnana Bharathy2Bhuva Narayan3Mukesh Prasad4School of Computer Science, FEIT, University of Technology Sydney, Sydney, NSW 2007, AustraliaDepartment of Information Technology, Delhi Technological University, Delhi 110042, IndiaSchool of Computer Science, FEIT, University of Technology Sydney, Sydney, NSW 2007, AustraliaSchool of Communication, FASS, University of Technology Sydney, Sydney, NSW 2007, AustraliaSchool of Computer Science, FEIT, University of Technology Sydney, Sydney, NSW 2007, AustraliaThe rise in web and social media interactions has resulted in the efortless proliferation of offensive language and hate speech. Such online harassment, insults, and attacks are commonly termed cyberbullying. The sheer volume of user-generated content has made it challenging to identify such illicit content. Machine learning has wide applications in text classification, and researchers are shifting towards using deep neural networks in detecting cyberbullying due to the several advantages they have over traditional machine learning algorithms. This paper proposes a novel neural network framework with parameter optimization and an algorithmic comparative study of eleven classification methods: four traditional machine learning and seven shallow neural networks on two real world cyberbullying datasets. In addition, this paper also examines the effect of feature extraction and word-embedding-techniques-based natural language processing on algorithmic performance. Key observations from this study show that bidirectional neural networks and attention models provide high classification results. Logistic Regression was observed to be the best among the traditional machine learning classifiers used. Term Frequency-Inverse Document Frequency (TF-IDF) demonstrates consistently high accuracies with traditional machine learning techniques. Global Vectors (GloVe) perform better with neural network models. Bi-GRU and Bi-LSTM worked best amongst the neural networks used. The extensive experiments performed on the two datasets establish the importance of this work by comparing eleven classification methods and seven feature extraction techniques. Our proposed shallow neural networks outperform existing state-of-the-art approaches for cyberbullying detection, with accuracy and F1-scores as high as ~95% and ~98%, respectively.https://www.mdpi.com/2079-9292/10/22/2810cyberbullyinghate speechoffensive languagemachine learningneural networksdeep learning |
spellingShingle | Chahat Raj Ayush Agarwal Gnana Bharathy Bhuva Narayan Mukesh Prasad Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques Electronics cyberbullying hate speech offensive language machine learning neural networks deep learning |
title | Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques |
title_full | Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques |
title_fullStr | Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques |
title_full_unstemmed | Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques |
title_short | Cyberbullying Detection: Hybrid Models Based on Machine Learning and Natural Language Processing Techniques |
title_sort | cyberbullying detection hybrid models based on machine learning and natural language processing techniques |
topic | cyberbullying hate speech offensive language machine learning neural networks deep learning |
url | https://www.mdpi.com/2079-9292/10/22/2810 |
work_keys_str_mv | AT chahatraj cyberbullyingdetectionhybridmodelsbasedonmachinelearningandnaturallanguageprocessingtechniques AT ayushagarwal cyberbullyingdetectionhybridmodelsbasedonmachinelearningandnaturallanguageprocessingtechniques AT gnanabharathy cyberbullyingdetectionhybridmodelsbasedonmachinelearningandnaturallanguageprocessingtechniques AT bhuvanarayan cyberbullyingdetectionhybridmodelsbasedonmachinelearningandnaturallanguageprocessingtechniques AT mukeshprasad cyberbullyingdetectionhybridmodelsbasedonmachinelearningandnaturallanguageprocessingtechniques |