Enhancing Propaganda Detection in Arabic News Context Through Multi-Task Learning
Source abstract
Abstract
Social media has become a platform for the rapid spread of persuasion techniques that can negatively affect individuals and society. Propaganda detection, a crucial task in natural language processing, aims to identify manipulative content in texts, particularly in news media, by assessing propagandistic intent. Although extensively studied in English, Arabic propaganda detection remains challenging because of the language’s morphological complexity and limited resources. Furthermore, most research has treated propaganda detection as an isolated task, neglecting the influence of sentiments and emotions. The current study addresses this gap by introducing the first multi-task learning (MTL) models for Arabic propaganda detection, integrating sentiment analysis and emotion detection as auxiliary tasks. Three MTL models are introduced: (1) MTL combining all tasks, (2) PSMTL (propaganda and sentiment), and (3) PEMTL (propaganda and emotion) based on transformer architectures. Additionally, seven task-weighting schemes are proposed and evaluated. Experiments demonstrated the superiority of our framework over state-of-the-art methods, achieving a Macro-F1 score of 0.778 and 79% accuracy. The results highlight the importance of integrating sentiment and emotion for enhanced propaganda detection; demonstrate that MTL improves model performance; and provide valuable insights into the interaction among sentiment, emotion, and propaganda.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Misinformation and Its Impacts · Hate Speech and Cyberbullying Detection · Spam and Phishing Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
STC’s Artificial Intelligence Chair, Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia
Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 2614, Riyadh 13312, Saudi Arabia
Department of Computer Science, College of Computer and Information Sciences, Majmaah University, Al-Majmaah 11952, Saudi Arabia
Department of Information Technology, College of Computer and Information Sciences, King Saud University, P.O. Box 2614, Riyadh 13312, Saudi Arabia
Funding
Deanship of Scientific Research, King Saud University
References (60)
Show source-provided references
1. (2024, February 13). Digital Around the World. DataReportal—Global Digital Insights. Available online: https://datareportal.com/global-digital-overview.
2. (2024, February 13). PROPAGANDA|English Meaning—Cambridge Dictionary. Available online: https://dictionary.cambridge.org/dictionary/english/propaganda.
3. Girshick, R. (2015). Fast R-CNN. arXiv, Available online: http://arxiv.org/abs/1504.08083.
4. Collobert, R., and Weston, J. (2008, January 5–9). A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland.10.1145/1390156.1390177 ↗
5. Liu, X., He, P., Chen, W., and Gao, J. (August, January 28). Multi-Task Deep Neural Networks for Natural Language Understanding. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
6. Alrashidi, B., Jamal, A., and Alkhathlan, A. (2023). Abusive Content Detection in Arabic Tweets Using Multi-Task Learning and Transformer-Based Models. Appl. Sci., 13.10.3390/app13105825 ↗
7. Fadel, A., Saleh, M., Salama, R., and Abulnaja, O. (2024). MTL-AraBERT: An Enhanced Multi-Task Learning Model for Arabic Aspect-Based Sentiment Analysis. Computers, 13.10.3390/computers13040098 ↗
8. Mahdaouy, A.E., Mekki, A.E., Essefar, K., Mamoun, N.E., Berrada, I., and Khoumsi, A. (2021). Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language. arXiv.
9. Ruder, S. (2019). Neural Transfer Learning for Natural Language Processing. [Ph.D. Thesis, NUI Galway].10.18653/v1/N19-5004 ↗
10. Niehues, J., and Cho, E. (2017, January 7–8). Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning. Proceedings of the Second Conference on Machine Translation, Copenhagen, Denmark.10.18653/v1/W17-4708 ↗
11. Zhang, Y., and Yang, Q. (2021). A Survey on Multi-Task Learning. arXiv.
12. Ruder, S. (2017). An Overview of Multi-Task Learning in Deep Neural Networks. arXiv.
13. (2024, February 17). Top Ten Internet Languages in The World—Internet Statistics. Available online: https://www.internetworldstats.com/stats7.htm#google_vignette.
14. Darwish, K., Habash, N., Abbas, M., Al-Khalifa, H., Al-Natsheh, H.T., Bouamor, H., Bouzoubaa, K., Cavalli-Sforza, V., El-Beltagy, S.R., and El-Hajj, W. (2021). A Panoramic Survey of Natural Language Processing in the Arab World. arXiv, Available online: http://arxiv.org/abs/2011.12631.10.1145/3447735 ↗
15. Kaczyński, K., and Przybyła, P. (2021). HOMADOS at SemEval-2021 Task 6: Multi-Task Learning for Propaganda Detection. Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), Bangkok, Thailand, 5–6 August 2021, Association for Computational Linguistics.10.18653/v1/2021.semeval-1.141 ↗
16. Baraniak, K., and Sydow, M. (2023). Kb at SemEval-2023 Task 3: On Multitask Hierarchical BERT Base Neural Network for Multi-label Persuasion Techniques Detection. Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), Toronto, ON, Canada, 13–14 July 2023, Association for Computational Linguistics.10.18653/v1/2023.semeval-1.193 ↗
17. Attieh, J., and Hassan, F. (2022). Pythoneers at WANLP 2022 Shared Task: Monolingual AraBERT for Arabic Propaganda Detection and Span Extraction. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), Abu Dhabi, United Arab Emirates (Hybrid), 8 December 2022, Association for Computational Linguistics.10.18653/v1/2022.wanlp-1.64 ↗
18. Hadjer, K., and Bouklouha, T. (2023). HTE at ArAIEval Shared Task: Integrating Content Type Information in Binary Persuasive Technique Detection. Proceedings of the ArabicNLP 2023, Singapore, 23 November 2023, Association for Computational Linguistics.10.18653/v1/2023.arabicnlp-1.46 ↗
19. Shukla, U., Vyas, M., and Tiwari, S. (2023). Raphael at ArAIEval Shared Task: Understanding Persuasive Language and Tone, an LLM Approach. Proceedings of the ArabicNLP 2023, Singapore, 23 November 2023, Association for Computational Linguistics.10.18653/v1/2023.arabicnlp-1.60 ↗
20. Li, Y., Tian, X., Liu, T., and Tao, D. (2015, January 25–31). Multi-Task Model and Feature Joint Learning. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires, Argentina.
21. Mahabadi, R.K., Ruder, S., Dehghani, M., and Henderson, J. (2021). Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, 1–6 August 2021, Association for Computational Linguistics.
22. Al-Henaki, L., Al-Khalifa, H., Al-Salman, A., Alqubayshi, H., Al-Twailay, H., Alghamdi, G., and Aljasim, H. (2025). MultiProSE: A Multi-label Arabic Dataset for Propaganda, Sentiment, and Emotion Detection. arXiv.10.1007/978-3-031-97141-9_11 ↗
23. Hasanain, M., Ahmad, F., and Alam, F. (2024). Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles. arXiv.
24. Kmainasi, M.B., Shahroor, A.E., Hasanain, M., Laskar, S.R., Hassan, N., and Alam, F. (2024). LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content. arXiv.10.18653/v1/2025.findings-naacl.313 ↗
25. Al-Henaki, L., Al-Khalifa, H., and Al-Salman, A. (2025). Enhancing Arabic Propaganda Detection through Hybrid Learning and Lexicon-Based Feature Engineering. Computation, submitted.
26. Rashkin, H., Choi, E., Jang, J.Y., Volkova, S., and Choi, Y. (2017). Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 9–11 September 2017, Association for Computational Linguistics.10.18653/v1/D17-1317 ↗
27. Detecting Textual Propaganda Using Machine Learning Techniques10.21123/bsj.2021.18.1.0199 ↗
28. Proppy: Organizing the news based on their propagandistic content10.1016/j.ipm.2019.03.005 ↗
29. SVMBPI: Support Vector Machine-Based Propaganda Identification10.1007/978-981-16-1056-1_35 ↗
30. Gupta, P., Saxena, K., Yaseen, U., Runkler, T., and Schütze, H. (2019). Neural Architectures for Fine-Grained Propaganda Detection in News. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, Hong Kong, China, 4 November 2019, Association for Computational Linguistics.10.18653/v1/D19-5012 ↗
31. Li, J., Ye, Z., and Xiao, L. (2019). Detection of Propaganda Using Logistic Regression. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, Hong Kong, China, 4 November 2019, Association for Computational Linguistics.10.18653/v1/D19-5017 ↗
32. Khanday, A.M.U.D., Wani, M.A., Rabani, S.T., Khan, Q.R., and El-Latif, A.A.A. (2024). HAPI: An efficient Hybrid Feature Engineering-based Approach for Propaganda Identification in social media. PLoS ONE, 19.10.1371/journal.pone.0302583 ↗
33. Samir, A., Soliman, A.B., Ibrahim, M., Hesham, L., and El-Beltagy, S.R. (2022). NGU_CNLP at WANLP 2022 Shared Task: Propaganda Detection in Arabic. Proceedings of the Seventh Arabic Natural Language Processing, WANLP.
34. ProSOUL: A Framework to Identify Propaganda From Online Urdu Content10.1109/ACCESS.2020.3028131 ↗
35. Wang, L., Shen, X., de Melo, G., and Weikum, G. (2020). Cross-Domain Learning for Classifying Propaganda in Online Contents. arXiv.
36. Polonijo, B., Suman, S., and Simac, I. (2021). Propaganda Detection Using Sentiment Aware Ensemble Deep Learning. Proceedings of the 44th International Convention on Information, Communication and Electronic Technology (MIPRO), Opatija, Croatia, 27 September–1 October 2021, IEEE.10.23919/MIPRO52101.2021.9596654 ↗
37. Tiwari, P., and Eswari, R. (2023, January 20–21). An LSTM based Propaganda Detection System for News Articles. Proceedings of the 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), Ghaziabad, India.10.1109/CICTN57981.2023.10141017 ↗
38. Da San Martino, G., Barrón-Cedeño, A., Wachsmuth, H., Petrov, R., and Nakov, P. (2020). SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles. Proceedings of the Fourteenth Workshop on Semantic Evaluation, Barcelona, Spain, 12–13 December 2020, International Committee for Computational Linguistics.10.18653/v1/2020.semeval-1.186 ↗
39. Pauli, A., Derczynski, L., and Assent, I. (2022). Modelling Persuasion through Misuse of Rhetorical Appeals. Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI), Abu Dhabi, United Arab Emirates, 7 December 2022, Association for Computational Linguistics.10.18653/v1/2022.nlp4pi-1.11 ↗
40. Combating propaganda texts using transfer learning
41. Chavan, T., and Kane, A.M. (2022). ChavanKane at WANLP 2022 Shared Task: Large Language Models for Multi-label Propaganda Detection. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), Abu Dhabi, United Arab Emirates, 8 December 2022, Association for Computational Linguistics.10.18653/v1/2022.wanlp-1.60 ↗
42. Gaanoun, K., and Benelallam, I. (2022, January 8). SI2M & AIOX Labs at WANLP 2022 Shared Task: Propaganda Detection in Arabic, A Data Augmentation and Named Entity Recognition Approach. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), Abu Dhabi, United Arab Emirates.10.18653/v1/2022.wanlp-1.58 ↗
43. Laskar, S.R., Singh, R., Khilji, A.F.U.R., Manna, R., Pakray, P., and Bandyopadhyay, S. (2022). CNLP-NITS-PP at WANLP 2022 Shared Task: Propaganda Detection in Arabic using Data Augmentation and AraBERT Pre-trained Model. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), Abu Dhabi, United Arab Emirates, 8 December 2022, Association for Computational Linguistics.10.18653/v1/2022.wanlp-1.65 ↗
44. Lamsiyah, S., Mahdaouy, A., Alami, H., Berrada, I., and Schommer, C. (2023). UL & UM6P at ArAIEval Shared Task: Transformer-based model for Persuasion Techniques and Disinformation detection in Arabic. Proceedings of the ArabicNLP 2023, Singapore, 23 November 2023, Association for Computational Linguistics.10.18653/v1/2023.arabicnlp-1.55 ↗
45. Jarrar, M., Habash, H., and El-Haj, M. (2025). Integrating Argumentation Features for Enhanced Propaganda Detection in Arabic Narratives on the Israeli War on Gaza. Proceedings of the first International Workshop on Nakba Narratives as Language Resources, Online, 20 January 2025, Association for Computational Linguistics. Available online: https://aclanthology.org/2025.nakbanlp-1.14/.
46. Antoun, W., Baly, F., and Hajj, H. (2021). AraBERT: Transformer-based Model for Arabic Language Understanding. arXiv, Available online: http://arxiv.org/abs/2003.00104.
47. Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., and Macherey, K. (2016). Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv.
48. An overview of multi-task learning10.1093/nsr/nwx105 ↗
49. Vandenhende, S., Georgoulis, S., Proesmans, M., Dai, D., and Gool, L. (2020). Revisiting Multi-Task Learning in the Deep Learning Era. arXiv, Available online: https://www.semanticscholar.org/paper/6a248e075035cc6f17a64ed4336a507faad1f72e.
50. Chen, S., Zhang, Y., and Yang, Q. (2024). Multi-Task Learning in Natural Language Processing: An Overview. arXiv.10.1145/3663363 ↗
51. Liu, S., Johns, E., and Davison, A.J. (2019). End-to-End Multi-Task Learning with Attention. arXiv.10.1109/CVPR.2019.00197 ↗
52. Lin, B., Ye, F., Zhang, Y., and Tsang, I.W. (2021). Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning. arXiv.
53. Song, W., Song, Z., Liu, L., and Fu, R. (2020, January 11–17). Hierarchical Multi-task Learning for Organization Evaluation of Argumentative Student Essays. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence Organization, Yokohama, Japan.10.24963/ijcai.2020/536 ↗
54. Kendall, A., Gal, Y., and Cipolla, R. (2018). Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. arXiv.
55. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., and Funtowicz, M. (2020). Transformers: State-of-the-Art Natural Language Processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online, 16–20 November 2020, Association for Computational Linguistics.10.18653/v1/2020.emnlp-demos.6 ↗
56. Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv, Available online: http://arxiv.org/abs/1711.05101.
57. Liashchynskyi, P., and Liashchynskyi, P. (2019). Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS. arXiv.
58. Manning, C.D., Raghavan, P., and Schütze, H. (2009). Introduction to Information Retrieval, Cambridge University Press.10.1017/CBO9780511809071 ↗
59. Sanh, V., Wolf, T., and Ruder, S. (2018). A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks. arXiv.10.1609/aaai.v33i01.33016949 ↗
60. Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., and Finn, C. (2020). Gradient Surgery for Multi-Task Learning. arXiv.