Facebook pixel tracking

The Science and Information (SAI) Organization publishes open-access peer-reviewed journals in computer science and artificial intelligence.

Contact Info
Website thesai.org
Follow Us
Contact Info
Follow Us
Research Article | Open Access |

Multi-View Behavioral Probing for Political Bias in Arabic and Multilingual Transformers Before and After Domain Adaptation

Author 1: Ahmad Abdelhameed Author 2: Ensaf Hussein Mohamed Author 3: Walaa Medhat
International Journal of Advanced Computer Science and Applications (IJACSA) · Vol. 17, No. 4 · Published 2026

DOI: 10.14569/IJACSA.2026.0170412

Abstract

Political bias in transformer-based language models poses a critical challenge for applications involving politically sensitive Arabic news, yet systematic evaluation remains limited. This paper presents a multi-view behavioral framework to detect political bias in four pre-trained transformer models: AraBERTv2, CAMeLBERT, mBERT, and XLM-R. The framework integrates four complementary probes: sentiment drift, emotion drift, counterfactual actor-swapping for identity sensitivity, and masked language model probing to detect lexical preference shifts. Each model is evaluated before and after domain-adaptive fine-tuning on the FigNews Arabic political news dataset to analyze how politically sensitive training data influences representational bias. To synthesize signals from these probes, a Decision and Bias Reporting Agent (DBRA) aggregates the evidence using a structured hierarchy that prioritizes implicit bias indicators. Results show that bias is already present in base checkpoints and can significantly shift after adaptation. For example, mBERT’s masked preference for SideA drops from 40.7% to 0.0%, indicating complete directional collapse, while XLM-R shows a large increase in masked preference toward SideA (ΔPR = +32.8%).

Keywords

How to Cite this Article

Abdelhameed, A., Mohamed, E. H., & Medhat, W. (2026). Multi-View Behavioral Probing for Political Bias in Arabic and Multilingual Transformers Before and After Domain Adaptation. International Journal of Advanced Computer Science and Applications, 17(4). https://doi.org/10.14569/IJACSA.2026.0170412

Abdelhameed, Ahmad, et al.. "Multi-View Behavioral Probing for Political Bias in Arabic and Multilingual Transformers Before and After Domain Adaptation." International Journal of Advanced Computer Science and Applications, vol. 17, no. 4, 2026, https://doi.org/10.14569/IJACSA.2026.0170412.

@article{Abdelhameed2026,
  title     = {Multi-View Behavioral Probing for Political Bias in Arabic and Multilingual Transformers Before and After Domain Adaptation},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {4},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Ahmad Abdelhameed and Ensaf Hussein Mohamed and Walaa Medhat},
  doi       = {10.14569/IJACSA.2026.0170412},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170412}
}

Open Access — licensed under a Creative Commons Attribution 4.0 International License. Unrestricted use, distribution, and reproduction in any medium, even commercially, as long as the original work is properly cited.

Call for Papers - Important Dates

Volume 17 No. 12, December 2026
Paper Submission Due November 25, 2026
Review Notification December 15, 2026
Publication Date December 31, 2026