Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling
In today’s world, news outlets have changed dramatically; newspapers are obsolete, and radio is no longer in the picture. People look for news online and on social media, such as Twitter and Facebook. Social media contributors share information and trending stories before verifying their...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9931021/ |
| _version_ | 1811233078840918016 |
|---|---|
| author | Naelah O. Bahurmuz Ghada A. Amoudi Fatmah A. Baothman Amani T. Jamal Hanan S. Alghamdi Areej M. Alhothali |
| author_facet | Naelah O. Bahurmuz Ghada A. Amoudi Fatmah A. Baothman Amani T. Jamal Hanan S. Alghamdi Areej M. Alhothali |
| author_sort | Naelah O. Bahurmuz |
| collection | DOAJ |
| description | In today’s world, news outlets have changed dramatically; newspapers are obsolete, and radio is no longer in the picture. People look for news online and on social media, such as Twitter and Facebook. Social media contributors share information and trending stories before verifying their truthfulness, thus, spreading rumors. Early identification of rumors from social media has attracted many researchers. However, a relatively smaller number of studies focused on other languages, such as Arabic. In this study, an Arabic rumor detection model is proposed. The model was built using transformer-based deep learning architecture. According to the literature, transformers are neural networks with outstanding performance in natural language processing tasks. Two transformers-based models, AraBERT and MARBERT, were employed, tested, and evaluated using three recently developed Arabic datasets. These models are extensions to the BERT, Bidirectional Encoder Representations from Transformers, a deep learning model that uses transformer architecture to learn the text representations and leverages the attention mechanism. We have also mitigated the challenges introduced by the imbalanced training datasets by employing two sampling techniques. The experimental results of our proposed approaches achieved a maximum accuracy of 0.97. This result demonstrated the effectiveness of the proposed method and outperformed other existing Arabic rumor detection methods. |
| first_indexed | 2024-04-12T11:15:32Z |
| format | Article |
| id | doaj.art-235d8337f98344d2a37a5167e93ae955 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T11:15:32Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-235d8337f98344d2a37a5167e93ae9552022-12-22T03:35:31ZengIEEEIEEE Access2169-35362022-01-011011490711491810.1109/ACCESS.2022.32175229931021Arabic Rumor Detection Using Contextual Deep Bidirectional Language ModelingNaelah O. Bahurmuz0Ghada A. Amoudi1https://orcid.org/0000-0001-5640-7166Fatmah A. Baothman2https://orcid.org/0000-0003-0344-1007Amani T. Jamal3Hanan S. Alghamdi4https://orcid.org/0000-0003-2059-7687Areej M. Alhothali5https://orcid.org/0000-0001-9727-0178Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaIn today’s world, news outlets have changed dramatically; newspapers are obsolete, and radio is no longer in the picture. People look for news online and on social media, such as Twitter and Facebook. Social media contributors share information and trending stories before verifying their truthfulness, thus, spreading rumors. Early identification of rumors from social media has attracted many researchers. However, a relatively smaller number of studies focused on other languages, such as Arabic. In this study, an Arabic rumor detection model is proposed. The model was built using transformer-based deep learning architecture. According to the literature, transformers are neural networks with outstanding performance in natural language processing tasks. Two transformers-based models, AraBERT and MARBERT, were employed, tested, and evaluated using three recently developed Arabic datasets. These models are extensions to the BERT, Bidirectional Encoder Representations from Transformers, a deep learning model that uses transformer architecture to learn the text representations and leverages the attention mechanism. We have also mitigated the challenges introduced by the imbalanced training datasets by employing two sampling techniques. The experimental results of our proposed approaches achieved a maximum accuracy of 0.97. This result demonstrated the effectiveness of the proposed method and outperformed other existing Arabic rumor detection methods.https://ieeexplore.ieee.org/document/9931021/Classificationdeep learningfake newsimbalanced datamachine learningnatural language processing |
| spellingShingle | Naelah O. Bahurmuz Ghada A. Amoudi Fatmah A. Baothman Amani T. Jamal Hanan S. Alghamdi Areej M. Alhothali Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling IEEE Access Classification deep learning fake news imbalanced data machine learning natural language processing |
| title | Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling |
| title_full | Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling |
| title_fullStr | Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling |
| title_full_unstemmed | Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling |
| title_short | Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling |
| title_sort | arabic rumor detection using contextual deep bidirectional language modeling |
| topic | Classification deep learning fake news imbalanced data machine learning natural language processing |
| url | https://ieeexplore.ieee.org/document/9931021/ |
| work_keys_str_mv | AT naelahobahurmuz arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling AT ghadaaamoudi arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling AT fatmahabaothman arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling AT amanitjamal arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling AT hanansalghamdi arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling AT areejmalhothali arabicrumordetectionusingcontextualdeepbidirectionallanguagemodeling |