HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network
Adversaries and anti-social elements have exploited the rapid proliferation of computing technology and online social media in the form of novel security threats, such as fake profiles, hate speech, social bots, and rumors. The hate speech problem on online social networks (OSNs) is also widespread....
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9682725/ |
| _version_ | 1823966646213017600 |
|---|---|
| author | Shakir Khan Ashraf Kamal Mohd Fazil Mohammed Ali Alshara Vineet Kumar Sejwal Reemiah Muneer Alotaibi Abdul Rauf Baig Salihah Alqahtani |
| author_facet | Shakir Khan Ashraf Kamal Mohd Fazil Mohammed Ali Alshara Vineet Kumar Sejwal Reemiah Muneer Alotaibi Abdul Rauf Baig Salihah Alqahtani |
| author_sort | Shakir Khan |
| collection | DOAJ |
| description | Adversaries and anti-social elements have exploited the rapid proliferation of computing technology and online social media in the form of novel security threats, such as fake profiles, hate speech, social bots, and rumors. The hate speech problem on online social networks (OSNs) is also widespread. The existing literature has machine learning approaches for hate speech detection on OSNs. However, the effectiveness of contextual information at different orientations is understudied. This study presents a novel <italic>Convolutional</italic>, <italic>BiGRU</italic>, and <italic>Capsule</italic> network-based deep learning model, HCovBi-Caps, to classify the hate speech. The proposed model is evaluated over two Twitter-based benchmark datasets – DS1(balanced) and DS2(unbalanced) with the best performance of 0.90, 0.80, and 0.84 respectively considering <italic>precision</italic>, <italic>recall</italic>, and <italic>f-score</italic> over unbalanced dataset. In terms of training and validation accuracy, the proposed model shows the best performance of 0.93 and 0.90, respectively, over the unbalanced dataset. In comparative evaluation, HCovBi-Caps demonstrates a significantly better performance than state-of-the-art approaches. In addition, HCovBi-Caps shows comparatively better performance over the unbalanced dataset. We also investigate the impact of different hyperparameters on the efficacy of HCovBi-Caps to ascertain the selection of their values. We observed that a higher value of <italic>routing iterations</italic> adversely affects the model performance, whereas a higher value of <italic>capsule dimension</italic> improves the performance. |
| first_indexed | 2024-12-17T18:15:47Z |
| format | Article |
| id | doaj.art-1d97048da32849e983273e8967c4374b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T18:15:47Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1d97048da32849e983273e8967c4374b2022-12-21T21:37:42ZengIEEEIEEE Access2169-35362022-01-01107881789410.1109/ACCESS.2022.31437999682725HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule NetworkShakir Khan0https://orcid.org/0000-0002-7925-9191Ashraf Kamal1https://orcid.org/0000-0002-8344-3792Mohd Fazil2https://orcid.org/0000-0001-8850-9845Mohammed Ali Alshara3https://orcid.org/0000-0002-6892-5400Vineet Kumar Sejwal4https://orcid.org/0000-0002-2316-4855Reemiah Muneer Alotaibi5Abdul Rauf Baig6https://orcid.org/0000-0003-1986-0636Salihah Alqahtani7College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaACL Digital, Bengaluru, IndiaDepartment of Computer Engineering, Qatar University, QatarCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaDepartment of Computer Science, Jamia Millia Islamia, New Delhi, IndiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaAdversaries and anti-social elements have exploited the rapid proliferation of computing technology and online social media in the form of novel security threats, such as fake profiles, hate speech, social bots, and rumors. The hate speech problem on online social networks (OSNs) is also widespread. The existing literature has machine learning approaches for hate speech detection on OSNs. However, the effectiveness of contextual information at different orientations is understudied. This study presents a novel <italic>Convolutional</italic>, <italic>BiGRU</italic>, and <italic>Capsule</italic> network-based deep learning model, HCovBi-Caps, to classify the hate speech. The proposed model is evaluated over two Twitter-based benchmark datasets – DS1(balanced) and DS2(unbalanced) with the best performance of 0.90, 0.80, and 0.84 respectively considering <italic>precision</italic>, <italic>recall</italic>, and <italic>f-score</italic> over unbalanced dataset. In terms of training and validation accuracy, the proposed model shows the best performance of 0.93 and 0.90, respectively, over the unbalanced dataset. In comparative evaluation, HCovBi-Caps demonstrates a significantly better performance than state-of-the-art approaches. In addition, HCovBi-Caps shows comparatively better performance over the unbalanced dataset. We also investigate the impact of different hyperparameters on the efficacy of HCovBi-Caps to ascertain the selection of their values. We observed that a higher value of <italic>routing iterations</italic> adversely affects the model performance, whereas a higher value of <italic>capsule dimension</italic> improves the performance.https://ieeexplore.ieee.org/document/9682725/Hate speech detectionTwitter data analysisconvolutional layercapsule networkBiGRUdeep learning |
| spellingShingle | Shakir Khan Ashraf Kamal Mohd Fazil Mohammed Ali Alshara Vineet Kumar Sejwal Reemiah Muneer Alotaibi Abdul Rauf Baig Salihah Alqahtani HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network IEEE Access Hate speech detection Twitter data analysis convolutional layer capsule network BiGRU deep learning |
| title | HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network |
| title_full | HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network |
| title_fullStr | HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network |
| title_full_unstemmed | HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network |
| title_short | HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network |
| title_sort | hcovbi caps hate speech detection using convolutional and bi directional gated recurrent unit with capsule network |
| topic | Hate speech detection Twitter data analysis convolutional layer capsule network BiGRU deep learning |
| url | https://ieeexplore.ieee.org/document/9682725/ |
| work_keys_str_mv | AT shakirkhan hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT ashrafkamal hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT mohdfazil hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT mohammedalialshara hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT vineetkumarsejwal hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT reemiahmuneeralotaibi hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT abdulraufbaig hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork AT salihahalqahtani hcovbicapshatespeechdetectionusingconvolutionalandbidirectionalgatedrecurrentunitwithcapsulenetwork |