The dialects gap: A multi-task learning approach for enhancing hate speech detection in Arabic dialects
Hate speech is a complex and often debated concept within Arabic dialects. Handling and detecting hate speech in Arabic poses unique challenges due to the diverse dialects that exhibit several linguistic variations, whether in meaning or context. Previous studies have often used multiple Arabic dial...
Saved in:
| Published in: | Expert systems with applications Vol. 295; p. 128584 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.01.2026
|
| Subjects: | |
| ISSN: | 0957-4174 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Hate speech is a complex and often debated concept within Arabic dialects. Handling and detecting hate speech in Arabic poses unique challenges due to the diverse dialects that exhibit several linguistic variations, whether in meaning or context. Previous studies have often used multiple Arabic dialects combined within a single corpus without specifying the dialects used, which is problematic because it can lead to misidentification of hateful and non-hateful contexts related to a particular dialect. This research therefore aims to address the challenge of dialectal variation ambiguity, which has led to polarity misidentification in previous studies that often fail to distinguish between contexts or terms that have the same form and carry different meanings across different Arabic dialects. In this paper, we propose a multi-task learning approach built upon transformer architecture to bridge this gap in hate speech detection across Arabic dialects. Using publicly available datasets from various dialects, the proposed model is designed to identify and distinguish subtle hate speech patterns and use shared representation knowledge across five Arabic dialects: Egyptian, Saudi, Levant, Gulf, and Algerian. To the best of our knowledge, it is the first model to simultaneously address multiple dialects and recognize hate speech by using the distinctive characteristics of each dialect. Our findings show that the proposed model makes a significant contribution to advancing hate speech detection in the Arabic language, surpassing single-task models. It achieved F1 scores of 0.98, 0.84, 0.85, 0.76, and 0.80 for the respective dialects of Egyptian, Levant, Saudi, Algerian, and Gulf, representing overall improvements of 14% compared to previous research. These results showcase the effectiveness of our approach, demonstrating not only high performance but also an accurate understanding of dialect-specific hate speech. |
|---|---|
| AbstractList | Hate speech is a complex and often debated concept within Arabic dialects. Handling and detecting hate speech in Arabic poses unique challenges due to the diverse dialects that exhibit several linguistic variations, whether in meaning or context. Previous studies have often used multiple Arabic dialects combined within a single corpus without specifying the dialects used, which is problematic because it can lead to misidentification of hateful and non-hateful contexts related to a particular dialect. This research therefore aims to address the challenge of dialectal variation ambiguity, which has led to polarity misidentification in previous studies that often fail to distinguish between contexts or terms that have the same form and carry different meanings across different Arabic dialects. In this paper, we propose a multi-task learning approach built upon transformer architecture to bridge this gap in hate speech detection across Arabic dialects. Using publicly available datasets from various dialects, the proposed model is designed to identify and distinguish subtle hate speech patterns and use shared representation knowledge across five Arabic dialects: Egyptian, Saudi, Levant, Gulf, and Algerian. To the best of our knowledge, it is the first model to simultaneously address multiple dialects and recognize hate speech by using the distinctive characteristics of each dialect. Our findings show that the proposed model makes a significant contribution to advancing hate speech detection in the Arabic language, surpassing single-task models. It achieved F1 scores of 0.98, 0.84, 0.85, 0.76, and 0.80 for the respective dialects of Egyptian, Levant, Saudi, Algerian, and Gulf, representing overall improvements of 14% compared to previous research. These results showcase the effectiveness of our approach, demonstrating not only high performance but also an accurate understanding of dialect-specific hate speech. |
| ArticleNumber | 128584 |
| Author | Abdelsamie, Mahmoud Mohamed Azab, Shahira Shaaban Hefny, Hesham A. |
| Author_xml | – sequence: 1 givenname: Mahmoud Mohamed surname: Abdelsamie fullname: Abdelsamie, Mahmoud Mohamed email: 12422021452995@pg.cu.edu.eg – sequence: 2 givenname: Shahira Shaaban orcidid: 0000-0001-6903-272X surname: Azab fullname: Azab, Shahira Shaaban email: Shahiraazazy@cu.edu.eg – sequence: 3 givenname: Hesham A. surname: Hefny fullname: Hefny, Hesham A. email: hehefny@cu.edu.eg |
| BookMark | eNp9kMtOwzAQRb0oEm3hB1j5BxJsx4lTxKaqeEmV2JS1NXHGjUvqRHYA8fckCmLJaqQ7ukdXZ0UWvvNIyA1nKWe8uD2lGL8gFUzkKRdlXsoFWbJNrhLJlbwkqxhPjHHFmFqS46FBWjto0QyRHqG_o1t6_mgHlwwQ32mLELzzRwp9HzowDbVdoOgb8GaKGxiQxh5x_NQ4jBTXeeo83QaonPlDX5ELC23E69-7Jm-PD4fdc7J_fXrZbfeJEXk2JHaDmZUVE5LnslJFbVSmqhwrk6EtTVkUlTWSs0xwyQplN7WwaLAGxrkArLI1ETPXhC7GgFb3wZ0hfGvO9KRHn_SkR0969KxnLN3PJRyXfToMOhqHfuS6MI7Xdef-q_8AGZRzwA |
| Cites_doi | 10.18653/v1/2021.acl-long.551 10.1007/s13278-024-01258-1 10.1007/978-3-030-32959-4_18 10.1016/j.eswa.2023.121031 10.12785/ijcds/130177 10.1007/s43926-023-00030-9 10.1109/ASONAM.2018.8508247 10.1016/j.osnem.2020.100096 10.1016/j.compeleceng.2024.109153 10.1017/S1351324923000402 10.1109/IALP57159.2022.9961263 10.11591/ijeecs.v25.i3.pp1712-1722 10.3390/informatics8040069 10.3390/app13105825 10.1016/j.eswa.2023.121115 10.18653/v1/W17-3008 10.1016/j.jksuci.2019.01.005 10.18653/v1/N18-2019 10.1016/j.heliyon.2023.e18647 10.1109/TKDE.2021.3070203 10.1109/ESOLEC54569.2022.10009167 10.18653/v1/W19-3512 10.1007/s13278-022-00950-4 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.eswa.2025.128584 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_eswa_2025_128584 S0957417425022031 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMVD ABUCO ABUFD ACDAQ ACGFS ACHRH ACLOT ACNTT ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGHFR AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALEQD ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APLSM APXCP AXJTR BJAXD BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFKBS EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SSL SST SSV SSZ T5K TN5 ~G- ~HD 29G 9DU AAAKG AAQXK AAYXX ABKBG ABWVN ABXDB ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET WUQ XPP ZMT |
| ID | FETCH-LOGICAL-c253t-f9e3f4b024154b76dc737b5ebc3ef8c866bfc4103214067f9d2feceda0112aeb3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001529393500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0957-4174 |
| IngestDate | Thu Nov 27 01:03:01 EST 2025 Sat Nov 29 17:07:55 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Multi-task learning (MTL) Hate speech AraBERT Offensive language Arabic dialects MARBERTv2 MARBERT |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c253t-f9e3f4b024154b76dc737b5ebc3ef8c866bfc4103214067f9d2feceda0112aeb3 |
| ORCID | 0000-0001-6903-272X |
| ParticipantIDs | crossref_primary_10_1016_j_eswa_2025_128584 elsevier_sciencedirect_doi_10_1016_j_eswa_2025_128584 |
| PublicationCentury | 2000 |
| PublicationDate | 2026-01-01 2026-01-00 |
| PublicationDateYYYYMMDD | 2026-01-01 |
| PublicationDate_xml | – month: 01 year: 2026 text: 2026-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2026 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Albadi, N., Kurdi, M., Mishra, S., 2018. Are they Our Brothers? Analysis and Detection of Religious Hate Speech in the Arabic Twittersphere. https://doi.org/10.1109/asonam.2018.8508247. Alkhamissi, B., Diab, M., 2022. Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification [WWW Document]. ACL Anthology. URL https://aclanthology.org/2022.osact-1.24. Aldjanabi, Dahou, Al-Qaness, Elaziz, Helmi, Damaševičius (b0030) 2021; 8 HMubarak, H., Darwish, K., Magdy, W., 2017. Abusive Language Detection on Arabic Social Media. https://doi.org/10.18653/v1/w17-3008. Qian, J., ElSherief, M., Belding, E., Wang, W.Y., 2018. Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection. https://doi.org/10.18653/v1/n18-2019. Antoun, W., Baly, F., Hajj, H., 2020. AraBERT: Transformer-based Model for Arabic Language Understanding [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.2. Elzayady, Mohamed, Badran, Salama (b0070) 2022; 25 Farha, I.A., Magdy, W., 2020. Multitask Learning for Arabic Offensive Language and Hate-Speech Detection [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.14. Husain, F., Uzuner, O., 2022. Transfer Learning Across Arabic Dialects for Offensive Language Detection. https://doi.org/10.1109/ialp57159.2022.9961263. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I., 2017. Attention Is All You Need. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1706.03762. Khezzar, Moursi, Aghbari (b0100) 2023; 3 Mazari, Kheddar (b0120) 2023; 13 Alsafari, Sadaoui, Mouhoub (b0045) 2020; 19 Ibrohim, Budi (b0095) 2023; 9 Haddad, Mulki, Oueslati (b0085) 2019 AbdelHamid, Jafar, Rahal (b0005) 2022; 12 Abdul-Mageed, M., Elmadany, A., Nagoudi, E.M.B., 2021. ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic. https://doi.org/10.18653/v1/2021.acl-long.551. Mubarak, H., Hassan, S., Chowdhury, S.A., 2022. Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2201.06723. Mulki, H., Haddad, H., Ali, C.B., Alshabani, H., 2019. L-HSAB: A Levantine Twitter Dataset for Hate Speech and Abusive Language. https://doi.org/10.18653/v1/w19-3512. Mahdaouy, A.E., Mekki, A.E., Essefar, K., Mamoun, N.E., Berrada, I., Khoumsi, A., 2021. Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language [WWW Document]. ACL Anthology. URL https://aclanthology.org/2021.wanlp-1.42. Nockleby, J. T. (2000). Hate speech. In L. W. Levy, & K. L. Karst (Eds.), Encyclopedia of the American Constitution (vol. 3, 2nd ed., pp. 1277–1279). Macmillan Reference USA. Ahmed, I., Abbas, M., Hatem, R., Ihab, A., Fahkr, M.W., 2022. Fine-tuning arabic pre-trained transformer models for egyptian-arabic dialect offensive language and hate speech detection and classification. https://doi.org/10.1109/esolec54569.2022.10009167. Mulki, H., Ghanem, B., 2021. Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language [WWW Document]. ACL Anthology. URL https://aclanthology.org/2021.wanlp-1.16. Elghannam (b0065) 2021; 33 Kibriya, Siddiqa, Khan, Khan (b0105) 2024; 116 Alshaalan, R., Al-Khalifa, H., 2020. Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.wanlp-1.2. Abdelsamie, Azab, Hefny (b0010) 2024; 14 Firmino, de Souza Baptista, de Paiva (b0080) 2024; 235 Alrashidi, Jamal, Alkhathlan (b0040) 2023; 13 Djandji, M., Baly, F., Antoun, W., Hajj, H., 2020. Multi-Task Learning using AraBert for Offensive Language Detection [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.16. Zhang, Yang (b0160) 2022; 34 Liu, Xu, Zhao, Zeng, Hu, Zhang, Luo, Cao (b0110) 2023; 234 Abdelsamie (10.1016/j.eswa.2025.128584_b0010) 2024; 14 Zhang (10.1016/j.eswa.2025.128584_b0160) 2022; 34 10.1016/j.eswa.2025.128584_b0090 Alrashidi (10.1016/j.eswa.2025.128584_b0040) 2023; 13 10.1016/j.eswa.2025.128584_b0050 Elzayady (10.1016/j.eswa.2025.128584_b0070) 2022; 25 10.1016/j.eswa.2025.128584_b0075 Ibrohim (10.1016/j.eswa.2025.128584_b0095) 2023; 9 10.1016/j.eswa.2025.128584_b0130 10.1016/j.eswa.2025.128584_b0150 10.1016/j.eswa.2025.128584_b0135 10.1016/j.eswa.2025.128584_b0035 10.1016/j.eswa.2025.128584_b0155 Aldjanabi (10.1016/j.eswa.2025.128584_b0030) 2021; 8 10.1016/j.eswa.2025.128584_b0055 10.1016/j.eswa.2025.128584_b0115 10.1016/j.eswa.2025.128584_b0015 Firmino (10.1016/j.eswa.2025.128584_b0080) 2024; 235 Mazari (10.1016/j.eswa.2025.128584_b0120) 2023; 13 Kibriya (10.1016/j.eswa.2025.128584_b0105) 2024; 116 Alsafari (10.1016/j.eswa.2025.128584_b0045) 2020; 19 10.1016/j.eswa.2025.128584_b0060 10.1016/j.eswa.2025.128584_b0020 Liu (10.1016/j.eswa.2025.128584_b0110) 2023; 234 10.1016/j.eswa.2025.128584_b0140 AbdelHamid (10.1016/j.eswa.2025.128584_b0005) 2022; 12 10.1016/j.eswa.2025.128584_b0025 10.1016/j.eswa.2025.128584_b0145 Haddad (10.1016/j.eswa.2025.128584_b0085) 2019 Khezzar (10.1016/j.eswa.2025.128584_b0100) 2023; 3 Elghannam (10.1016/j.eswa.2025.128584_b0065) 2021; 33 10.1016/j.eswa.2025.128584_b0125 |
| References_xml | – reference: Alshaalan, R., Al-Khalifa, H., 2020. Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.wanlp-1.2. – volume: 13 start-page: 965 year: 2023 end-page: 972 ident: b0120 article-title: Deep learning-based analysis of algerian dialect dataset targeted hate speech, offensive language and cyberbullying publication-title: International Journal of Computing and Digital System/International Journal of Computing and Digital Systems – volume: 13 start-page: 5825 year: 2023 ident: b0040 article-title: Abusive content detection in arabic tweets using multi-task learning and transformer-based models publication-title: Applied Sciences – volume: 19 year: 2020 ident: b0045 article-title: Hate and offensive speech detection on Arabic social media publication-title: Online Social Networks and Media – reference: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I., 2017. Attention Is All You Need. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1706.03762. – reference: Ahmed, I., Abbas, M., Hatem, R., Ihab, A., Fahkr, M.W., 2022. Fine-tuning arabic pre-trained transformer models for egyptian-arabic dialect offensive language and hate speech detection and classification. https://doi.org/10.1109/esolec54569.2022.10009167. – volume: 8 start-page: 69 year: 2021 ident: b0030 article-title: Arabic offensive and hate speech detection using a cross-corpora multi-task learning model publication-title: Informatics – volume: 33 start-page: 235 year: 2021 end-page: 242 ident: b0065 article-title: Text representation and classification based on bi-gram alphabet publication-title: Journal of King Saud University Computer and Information Sciences – volume: 34 start-page: 5586 year: 2022 end-page: 5609 ident: b0160 article-title: A survey on multi-task learning publication-title: IEEE Transactions on Knowledge and Data Engineering – reference: Djandji, M., Baly, F., Antoun, W., Hajj, H., 2020. Multi-Task Learning using AraBert for Offensive Language Detection [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.16. – volume: 3 year: 2023 ident: b0100 article-title: arHateDetector: Detection of hate speech from standard and dialectal Arabic Tweets publication-title: Discover Internet of Things – volume: 25 start-page: 1712 year: 2022 ident: b0070 article-title: Detecting Arabic textual threats in social media using artificial intelligence: An overview publication-title: Indonesian Journal of Electrical Engineering and Computer Science – reference: Mubarak, H., Hassan, S., Chowdhury, S.A., 2022. Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2201.06723. – volume: 12 year: 2022 ident: b0005 article-title: Levantine hate speech detection in twitter publication-title: Social Network Analysis and Mining – volume: 9 year: 2023 ident: b0095 article-title: Hate speech and abusive language detection in Indonesian social media: Progress and challenges publication-title: Heliyon – reference: Antoun, W., Baly, F., Hajj, H., 2020. AraBERT: Transformer-based Model for Arabic Language Understanding [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.2. – reference: Mulki, H., Ghanem, B., 2021. Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language [WWW Document]. ACL Anthology. URL https://aclanthology.org/2021.wanlp-1.16. – reference: HMubarak, H., Darwish, K., Magdy, W., 2017. Abusive Language Detection on Arabic Social Media. https://doi.org/10.18653/v1/w17-3008. – reference: Mulki, H., Haddad, H., Ali, C.B., Alshabani, H., 2019. L-HSAB: A Levantine Twitter Dataset for Hate Speech and Abusive Language. https://doi.org/10.18653/v1/w19-3512. – volume: 235 year: 2024 ident: b0080 article-title: Improving hate speech detection using cross-lingual learning publication-title: Expert Systems with Applications – reference: Farha, I.A., Magdy, W., 2020. Multitask Learning for Arabic Offensive Language and Hate-Speech Detection [WWW Document]. ACL Anthology. URL https://aclanthology.org/2020.osact-1.14. – reference: Qian, J., ElSherief, M., Belding, E., Wang, W.Y., 2018. Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection. https://doi.org/10.18653/v1/n18-2019. – reference: Nockleby, J. T. (2000). Hate speech. In L. W. Levy, & K. L. Karst (Eds.), Encyclopedia of the American Constitution (vol. 3, 2nd ed., pp. 1277–1279). Macmillan Reference USA. – reference: Mahdaouy, A.E., Mekki, A.E., Essefar, K., Mamoun, N.E., Berrada, I., Khoumsi, A., 2021. Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language [WWW Document]. ACL Anthology. URL https://aclanthology.org/2021.wanlp-1.42. – reference: Abdul-Mageed, M., Elmadany, A., Nagoudi, E.M.B., 2021. ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic. https://doi.org/10.18653/v1/2021.acl-long.551. – start-page: 251 year: 2019 end-page: 263 ident: b0085 article-title: T-HSAB: A tunisian hate speech and abusive dataset publication-title: Communications in Computer and Information Science – reference: Husain, F., Uzuner, O., 2022. Transfer Learning Across Arabic Dialects for Offensive Language Detection. https://doi.org/10.1109/ialp57159.2022.9961263. – volume: 116 year: 2024 ident: b0105 article-title: Towards safer online communities: Deep learning and explainable AI for hate speech detection and classification publication-title: Computers & Electrical Engineering – reference: Albadi, N., Kurdi, M., Mishra, S., 2018. Are they Our Brothers? Analysis and Detection of Religious Hate Speech in the Arabic Twittersphere. https://doi.org/10.1109/asonam.2018.8508247. – reference: Alkhamissi, B., Diab, M., 2022. Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification [WWW Document]. ACL Anthology. URL https://aclanthology.org/2022.osact-1.24. – volume: 234 year: 2023 ident: b0110 article-title: A cross-lingual transfer learning method for online COVID-19-related hate speech detection publication-title: Expert Systems with Applications – volume: 14 year: 2024 ident: b0010 article-title: A comprehensive review on Arabic offensive language and hate speech detection on social media: Methods, challenges and solutions publication-title: Social Network Analysis and Mining – ident: 10.1016/j.eswa.2025.128584_b0015 doi: 10.18653/v1/2021.acl-long.551 – ident: 10.1016/j.eswa.2025.128584_b0155 – ident: 10.1016/j.eswa.2025.128584_b0145 – volume: 14 year: 2024 ident: 10.1016/j.eswa.2025.128584_b0010 article-title: A comprehensive review on Arabic offensive language and hate speech detection on social media: Methods, challenges and solutions publication-title: Social Network Analysis and Mining doi: 10.1007/s13278-024-01258-1 – start-page: 251 year: 2019 ident: 10.1016/j.eswa.2025.128584_b0085 article-title: T-HSAB: A tunisian hate speech and abusive dataset publication-title: Communications in Computer and Information Science doi: 10.1007/978-3-030-32959-4_18 – volume: 234 year: 2023 ident: 10.1016/j.eswa.2025.128584_b0110 article-title: A cross-lingual transfer learning method for online COVID-19-related hate speech detection publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2023.121031 – ident: 10.1016/j.eswa.2025.128584_b0055 – volume: 13 start-page: 965 year: 2023 ident: 10.1016/j.eswa.2025.128584_b0120 article-title: Deep learning-based analysis of algerian dialect dataset targeted hate speech, offensive language and cyberbullying publication-title: International Journal of Computing and Digital System/International Journal of Computing and Digital Systems doi: 10.12785/ijcds/130177 – volume: 3 year: 2023 ident: 10.1016/j.eswa.2025.128584_b0100 article-title: arHateDetector: Detection of hate speech from standard and dialectal Arabic Tweets publication-title: Discover Internet of Things doi: 10.1007/s43926-023-00030-9 – ident: 10.1016/j.eswa.2025.128584_b0025 doi: 10.1109/ASONAM.2018.8508247 – ident: 10.1016/j.eswa.2025.128584_b0135 – volume: 19 year: 2020 ident: 10.1016/j.eswa.2025.128584_b0045 article-title: Hate and offensive speech detection on Arabic social media publication-title: Online Social Networks and Media doi: 10.1016/j.osnem.2020.100096 – volume: 116 year: 2024 ident: 10.1016/j.eswa.2025.128584_b0105 article-title: Towards safer online communities: Deep learning and explainable AI for hate speech detection and classification publication-title: Computers & Electrical Engineering doi: 10.1016/j.compeleceng.2024.109153 – ident: 10.1016/j.eswa.2025.128584_b0130 doi: 10.1017/S1351324923000402 – ident: 10.1016/j.eswa.2025.128584_b0090 doi: 10.1109/IALP57159.2022.9961263 – volume: 25 start-page: 1712 year: 2022 ident: 10.1016/j.eswa.2025.128584_b0070 article-title: Detecting Arabic textual threats in social media using artificial intelligence: An overview publication-title: Indonesian Journal of Electrical Engineering and Computer Science doi: 10.11591/ijeecs.v25.i3.pp1712-1722 – ident: 10.1016/j.eswa.2025.128584_b0060 – volume: 8 start-page: 69 year: 2021 ident: 10.1016/j.eswa.2025.128584_b0030 article-title: Arabic offensive and hate speech detection using a cross-corpora multi-task learning model publication-title: Informatics doi: 10.3390/informatics8040069 – volume: 13 start-page: 5825 year: 2023 ident: 10.1016/j.eswa.2025.128584_b0040 article-title: Abusive content detection in arabic tweets using multi-task learning and transformer-based models publication-title: Applied Sciences doi: 10.3390/app13105825 – volume: 235 year: 2024 ident: 10.1016/j.eswa.2025.128584_b0080 article-title: Improving hate speech detection using cross-lingual learning publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2023.121115 – ident: 10.1016/j.eswa.2025.128584_b0115 – ident: 10.1016/j.eswa.2025.128584_b0125 doi: 10.18653/v1/W17-3008 – volume: 33 start-page: 235 year: 2021 ident: 10.1016/j.eswa.2025.128584_b0065 article-title: Text representation and classification based on bi-gram alphabet publication-title: Journal of King Saud University Computer and Information Sciences doi: 10.1016/j.jksuci.2019.01.005 – ident: 10.1016/j.eswa.2025.128584_b0150 doi: 10.18653/v1/N18-2019 – ident: 10.1016/j.eswa.2025.128584_b0050 – volume: 9 year: 2023 ident: 10.1016/j.eswa.2025.128584_b0095 article-title: Hate speech and abusive language detection in Indonesian social media: Progress and challenges publication-title: Heliyon doi: 10.1016/j.heliyon.2023.e18647 – ident: 10.1016/j.eswa.2025.128584_b0035 – volume: 34 start-page: 5586 year: 2022 ident: 10.1016/j.eswa.2025.128584_b0160 article-title: A survey on multi-task learning publication-title: IEEE Transactions on Knowledge and Data Engineering doi: 10.1109/TKDE.2021.3070203 – ident: 10.1016/j.eswa.2025.128584_b0020 doi: 10.1109/ESOLEC54569.2022.10009167 – ident: 10.1016/j.eswa.2025.128584_b0075 – ident: 10.1016/j.eswa.2025.128584_b0140 doi: 10.18653/v1/W19-3512 – volume: 12 year: 2022 ident: 10.1016/j.eswa.2025.128584_b0005 article-title: Levantine hate speech detection in twitter publication-title: Social Network Analysis and Mining doi: 10.1007/s13278-022-00950-4 |
| SSID | ssj0017007 |
| Score | 2.4810994 |
| Snippet | Hate speech is a complex and often debated concept within Arabic dialects. Handling and detecting hate speech in Arabic poses unique challenges due to the... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 128584 |
| SubjectTerms | AraBERT Arabic dialects Hate speech MARBERT MARBERTv2 Multi-task learning (MTL) Offensive language |
| Title | The dialects gap: A multi-task learning approach for enhancing hate speech detection in Arabic dialects |
| URI | https://dx.doi.org/10.1016/j.eswa.2025.128584 |
| Volume | 295 |
| WOSCitedRecordID | wos001529393500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database issn: 0957-4174 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017007 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1JT9tAFB6lwKGXLkAF3TSH3qKJwoztsXuzKipaqQipVMrNmjUOEBMlhqL-if7lvsl4bANtVQ69ONHEfrb8vrxl3obQO3B7ZCqNJFZISyJGGRGgVwnTNtORTqzVYj1sgh8fp5NJdjIY_Ay1MNcXvKrSm5ts8V9ZDWvAbFc6-wB2t0RhAb4D0-EIbIfjPzPeVYOs0zSmYuFrz9eJg6QWq_MwKGLa9hP3bb-r0rXegOUSzM_hamEM_KJNbVTIh8yXQs5US_zWpr7rmFw3faFDxVwvNt5FmTQoYzH3UZEvopxfXmkQLKWYN1VW7qQfYh0l-lqKcrYU7lPIDsVHxla-rsKFq-bDfNTfuqD9rYuwB8lJdODH9ARxTLO4J1BBfcZ-htw9We-3Hc5GZvXdNZCi8ag7-XZj7TsKr01DDBluZ4WjUTgahafxCG1SHmcgJjfzT4eTz21gio99BX548qYOy6cM3n2S39s6Pfvl9Bl60jgeOPeAeY4GptpGT8NQD9zI-B00BfzgwGIM-HmPc9yhBwf04IAeDOjBLXqwQw_26MEtevCswh49Leld9O3j4emHI9JM4yCKxqwmNjPMRnLsTL5I8kQrzriMjVTM2FSlSSKtilx_RvDZEw5_dWqNMlqABqHCSPYCbVSXldlDmCZ8HAk1hsvBoNXgVUdK6AOmWJaAx2z20TC8t2Lhm64Uf-bVPorDqy0as9GbgwUg5S_XvXzQXV6hxx2EX6ONenll3qAtdV3PVsu3DUx-AWH_kXI |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+dialects+gap%3A+A+multi-task+learning+approach+for+enhancing+hate+speech+detection+in+Arabic+dialects&rft.jtitle=Expert+systems+with+applications&rft.au=Abdelsamie%2C+Mahmoud+Mohamed&rft.au=Azab%2C+Shahira+Shaaban&rft.au=Hefny%2C+Hesham+A.&rft.date=2026-01-01&rft.issn=0957-4174&rft.volume=295&rft.spage=128584&rft_id=info:doi/10.1016%2Fj.eswa.2025.128584&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_eswa_2025_128584 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |