Identifying Political Bias in Arabic News Articles

Saoussen Chaabane, Omar Trigui, Maher Jaoua


Abstract
A comprehensive framework was developed to detect political bias in Arabic news articles, with a case study focusing on media reporting of the Palestinian issue. The methodology integrates MARBERT contextual embeddings with classical and deep learning classifiers, including SVM, Logistic Regression, Random Forest, and LSTM. The scalability of data processing was ensured through Apache Spark for potential real-time deployment. Experimental results showed that fine-tuned MARBERT embeddings combined with LSTM achieved the highest classification accuracy of 0.87, along with notable improvements in F1-scores across the pro, against, and neutral categories. These findings highlight the effectiveness of domain-specific fine-tuning of transformer models for political bias classification. The study also addressed class imbalance using SMOTE and class weighting strategies, and assessed feature robustness using multiple vectorization techniques.
Anthology ID:
2026.politicalnlp-1.25
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Haithem Afli, Houda Bouamor, Wajdi Zaghouani, Sahar Ghannay, Shehenaz Hossain
Venues:
PoliticalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
228–233
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-politicalnlp-25
DOI:
10.63317/5a4k3eeanht5
Bibkey:
Cite (ACL):
Saoussen Chaabane, Omar Trigui, and Maher Jaoua. 2026. Identifying Political Bias in Arabic News Articles. In Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026), pages 228–233, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Identifying Political Bias in Arabic News Articles (Chaabane et al., PoliticalNLP 2026)
Copy Citation: