Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction
Since social media platforms are widely used and popular, they have given us more opportunities than we can even imagine. Despite all of the known benefits, some users may abuse these opportunities to humiliate, insult, bully, and harass other people. This issue explains why there is a need to reduc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/16/3567 |
| _version_ | 1797583947455004672 |
|---|---|
| author | Suliman Mohamed Fati Amgad Muneer Ayed Alwadain Abdullateef O. Balogun |
| author_facet | Suliman Mohamed Fati Amgad Muneer Ayed Alwadain Abdullateef O. Balogun |
| author_sort | Suliman Mohamed Fati |
| collection | DOAJ |
| description | Since social media platforms are widely used and popular, they have given us more opportunities than we can even imagine. Despite all of the known benefits, some users may abuse these opportunities to humiliate, insult, bully, and harass other people. This issue explains why there is a need to reduce such negative activities and create a safe cyberspace for innocent people by detecting cyberbullying activity. This study provides a comparative analysis of deep learning methods used to test and evaluate their effectiveness regarding a well-known global Twitter dataset. To recognize abusive tweets and overcome existing challenges, attention-based deep learning methods are introduced. The word2vec with CBOW concatenated formed the weights included in the embedding layer and was used to extract the features. The feature vector was input into a convolution and pooling mechanism, reducing the feature dimensionality while learning the position-invariant of the offensive words. A SoftMax function predicts feature classification. Using benchmark experimental datasets and well-known evaluation measures, the convolutional neural network model with attention-based long- and short-term memory was found to outperform other DL methods. The proposed cyberbullying detection methods were evaluated using benchmark experimental datasets and well-known evaluation measures. Finally, the results demonstrated the superiority of the attention-based 1D convolutional long short-term memory (Conv1DLSTM) classifier over the other implemented methods. |
| first_indexed | 2024-03-10T23:45:19Z |
| format | Article |
| id | doaj.art-28c936e7bfac481a86c370bf5a37fba0 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T23:45:19Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-28c936e7bfac481a86c370bf5a37fba02023-11-19T02:03:54ZengMDPI AGMathematics2227-73902023-08-011116356710.3390/math11163567Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature ExtractionSuliman Mohamed Fati0Amgad Muneer1Ayed Alwadain2Abdullateef O. Balogun3Information Systems Department, Prince Sultan University, Riyadh 11586, Saudi ArabiaDepartment of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USAComputer Science Department, Community College, King Saud University, Riyadh 11451, Saudi ArabiaDepartment of Computer and Information Sciences, Universiti Teknologi Petronas, Seri Iskandar 32160, MalaysiaSince social media platforms are widely used and popular, they have given us more opportunities than we can even imagine. Despite all of the known benefits, some users may abuse these opportunities to humiliate, insult, bully, and harass other people. This issue explains why there is a need to reduce such negative activities and create a safe cyberspace for innocent people by detecting cyberbullying activity. This study provides a comparative analysis of deep learning methods used to test and evaluate their effectiveness regarding a well-known global Twitter dataset. To recognize abusive tweets and overcome existing challenges, attention-based deep learning methods are introduced. The word2vec with CBOW concatenated formed the weights included in the embedding layer and was used to extract the features. The feature vector was input into a convolution and pooling mechanism, reducing the feature dimensionality while learning the position-invariant of the offensive words. A SoftMax function predicts feature classification. Using benchmark experimental datasets and well-known evaluation measures, the convolutional neural network model with attention-based long- and short-term memory was found to outperform other DL methods. The proposed cyberbullying detection methods were evaluated using benchmark experimental datasets and well-known evaluation measures. Finally, the results demonstrated the superiority of the attention-based 1D convolutional long short-term memory (Conv1DLSTM) classifier over the other implemented methods.https://www.mdpi.com/2227-7390/11/16/3567cyberbullyRNNCNNLSTMBiLSTMword2vec |
| spellingShingle | Suliman Mohamed Fati Amgad Muneer Ayed Alwadain Abdullateef O. Balogun Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction Mathematics cyberbully RNN CNN LSTM BiLSTM word2vec |
| title | Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction |
| title_full | Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction |
| title_fullStr | Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction |
| title_full_unstemmed | Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction |
| title_short | Cyberbullying Detection on Twitter Using Deep Learning-Based Attention Mechanisms and Continuous Bag of Words Feature Extraction |
| title_sort | cyberbullying detection on twitter using deep learning based attention mechanisms and continuous bag of words feature extraction |
| topic | cyberbully RNN CNN LSTM BiLSTM word2vec |
| url | https://www.mdpi.com/2227-7390/11/16/3567 |
| work_keys_str_mv | AT sulimanmohamedfati cyberbullyingdetectionontwitterusingdeeplearningbasedattentionmechanismsandcontinuousbagofwordsfeatureextraction AT amgadmuneer cyberbullyingdetectionontwitterusingdeeplearningbasedattentionmechanismsandcontinuousbagofwordsfeatureextraction AT ayedalwadain cyberbullyingdetectionontwitterusingdeeplearningbasedattentionmechanismsandcontinuousbagofwordsfeatureextraction AT abdullateefobalogun cyberbullyingdetectionontwitterusingdeeplearningbasedattentionmechanismsandcontinuousbagofwordsfeatureextraction |