Digital Islamic Humanities

Digital Islamic Humanities

Designing a Conceptual Model of Explainable Artificial Intelligence (XAI) Based on the clarification jihad Approach

Document Type : Original Article

Author
Mohammad Elyasi
Former PhD Student in Tourism, Master’s ,Degree in Tourism Marketing, Tehran university
10.22034/disah.2025.2076072.1054
Abstract
This study seeks to integrate the technical capabilities of Explainable Artificial Intelligence (XAI) with the strategic principles of clarification jihad, aiming to provide a transparent tool for clarifying decisions of intelligent systems, neutralizing misinformation, and enhancing the cognitive resilience of society. Adopting a problem-oriented approach, the study addresses two contemporary challenges: first, the “black-box” nature of AI systems; and second, the threat of cognitive warfare through the dissemination of fake news and information distortion. The research employs a qualitative-integrative and applied-developmental methodology. Data were collected through a systematic literature review, thematic analysis of the Supreme Leader’s statements from 2016 to 2025, and 10 semi-structured interviews with experts. Data analysis utilized reflexive thematic analysis and the design of a dynamic three-layer model. The findings resulted in a three-layer conceptual model: 1. Foundational Layer – clarification jihad: encompassing the mission of clarification, effective methods (explicitness, reasoning, audience analysis), and authentic religious content; 2. Intermediate Layer – Explainable AI: including technical-ethical capabilities (transparency, explainability, bias control) and technical requirements (indigenous knowledge bases, anti-bias systems); 3. Operational Outer Layer: featuring a human-centered approach, local infrastructure, and a management and evaluation system based on indicators and feedback cycles. The value-to-technology engine, aiming to translate clarification jihad principles into XAI requirements, alongside a combined jurisprudential-technical governance and feedback-driven lifecycle, transforms the clarification jihad concept from an abstract idea into an operational, value-oriented, dynamic, indigenous, and defensible system. This model provides an effective framework for countering cognitive warfare and advancing responsible AI within an Islamic discourse.
Keywords
Explainable Artificial Intelligence (XAI)
clarification jihad
Supreme Leader&‌‌rsquo
s Statements
Conceptual Model
Cognitive Defense
 
1. Amini, S. J., Mohammadian, M., & Salim, H. (2025/1404 SH). Strategic model for social media management in the field of clarification jihad. Religion and Communications (Imam Sadiq University / Nameh Sadiq). ([https://rc.isu.ac.ir/article_77669.html](https://rc.isu.ac.ir/article_77669.html))
2. Beheshtinejad, S. M., & Reza-zadeh, R. (2025/1404 SH). The role of clarification jihad in cyberspace for crisis prevention. Social Crisis Management, 17(1), 63–95. ([https://cmj.ihu.ac.ir/article_209951.html](https://cmj.ihu.ac.ir/article_209951.html))
3. Araqi, A., Bidgoli, M., & Rajabi Dehbarzouei, A. (2022/1401 SH). Analysis of the goals of enemy cognitive warfare and strategies for resilience with emphasis on Quranic teachings. Scientific Quarterly of Sacred Defense Studies, 8(4), 143–162. ([https://dor.isc.ac/dor/20.1001.1.37883674.1401.8.4.7.6](https://dor.isc.ac/dor/20.1001.1.37883674.1401.8.4.7.6))
4. Azizi, M., & Pirani, Sh. (2022/1401 SH). Software applications of cyberspace in clarification jihad. Scientific Quarterly of Islamic Revolution Research, 11(4). ([https://www.roir.ir/article_168676.html](https://www.roir.ir/article_168676.html))
5. Tabatabaei, S. F., Mohammad-Hossein-zadeh, A., & Akbarpour-Farsangi, S. (2023/1402 SH). Clarification jihad from the perspective of Ayatollah Khamenei and its jurisprudential foundations. Scientific Quarterly of Islamic Awakening Studies, 12(3), 143–168. ([https://www.iabaj.ir/article_180733.html](https://www.iabaj.ir/article_180733.html))
6. Ghaffari, S. A., Mahdian, H., Seydi, S., & Tarkashvand, J. (2024/1403 SH). A systematic model of clarification jihad in the thought of the Supreme Leader. Military Management Quarterly, 24(93), 1–27. ([https://jmm.iranjournals.ir/article_713680.html](https://jmm.iranjournals.ir/article_713680.html))
7. Mahjoob, H., & Shakouri, S. (2022/1401 SH). Modern cognitive warfare: from battlefield understanding to the cognitive warfare domain. Human Resources Studies, 12(2), 156–180. ([https://doi.org/10.22034/jhrs.2022.158895](https://doi.org/10.22034/jhrs.2022.158895))
8. Mahmoudi, M., & Sadeghi, S. (2022/1401 SH). Clarification jihad in cyberspace from the perspective of the Supreme Leader. In Third National Conference on Cyber Defense, Maragheh. ([https://civilica.com/doc/1493906](https://civilica.com/doc/1493906))
9. Malekzadeh, M. (2024/1403 SH). Functions and consequences of clarification jihad in the internationalization of the resistance model from Ayatollah Khamenei’s perspective. Military Management Quarterly, 24(10), 157–176. ([https://mag.rcipt.ir/article_181105.html](https://mag.rcipt.ir/article_181105.html))
10. Nikonehad, A., & Biouk, M. (2024/1403 SH). Designing and visualizing an optimal clarification jihad in confrontation with cognitive warfare based on the Supreme Leader’s thought. Islamic Revolution Futures Studies, 5(1), 11–36. ([https://dor.isc.ac/dor/20.1001.1.27173674.1403.5.1.1.3](https://dor.isc.ac/dor/20.1001.1.27173674.1403.5.1.1.3))
11. Rezaei, D., & Ebrahimi, H. (2024/1403 SH). Identifying factors, challenges, and strategies to counter cognitive warfare with focus on Generation Z in Iran. Air Defense Management Quarterly, 3(2), 27–42. ([https://jadm.khadu.ir/article_125.html?lang=fa](https://jadm.khadu.ir/article_125.html?lang=fa))
12. Extracts from the Supreme Leader’s statements on clarification jihad (2016–2025/1395–1404 SH). Official Website of the Office for Preservation and Publication of Ayatollah Khamenei’s Works. ([https://farsi.khamenei.ir/newspart-index-old?tid=26000#128187](https://farsi.khamenei.ir/newspart-index-old?tid=26000#128187))
13. Al Momani, I. (2025). Ethical challenges for using artificial intelligence in understanding Islamic jurisprudence. Salud, Ciencia y Tecnología-Serie de Conferencias, (4), 1519. ([http://dx.doi.org/10.56294/sctconf20251519](http://dx.doi.org/10.56294/sctconf20251519))
14. Al-Shammari, E. T. (2025, April). Culturally and computationally adaptive social robots for Arabophone Islamic societies. In 2024 International Conference on IT Innovation and Knowledge Discovery (ITIKD) (pp. 1–6). IEEE. ([https://doi.org/10.1109/ITIKD63574.2025.11005245](https://doi.org/10.1109/ITIKD63574.2025.11005245))
15. Arrieta, A. G. J., et al. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. ([https://doi.org/10.1016/j.inffus.2019.12.012](https://doi.org/10.1016/j.inffus.2019.12.012))
16. Babiker, A., et al. (2025). Attitude towards AI: Potential influence of conspiracy belief, XAI experience and locus of control. International Journal of Human–Computer Interaction, 41(13), 7939–7951. ([https://doi.org/10.1080/10447318.2024.2401249](https://doi.org/10.1080/10447318.2024.2401249))
17. Bang, T. C. (2024). Ensuring credibility and trustworthiness in qualitative inquiries. In Applied Linguistics and Language Education Research Methods: Fundamentals and Innovations (pp. 70–85). IGI Global. ([https://doi.org/10.4018/979-8-3693-2603-9.ch006](https://doi.org/10.4018/979-8-3693-2603-9.ch006))
18. Belghachi, M. (2023). A review on explainable artificial intelligence methods, applications, and challenges. Indonesian Journal of Electrical Engineering and Informatics (IJEEI), 11(4), 1007–1024. ([http://dx.doi.org/10.52549/ijeei.v11i4.5151](http://dx.doi.org/10.52549/ijeei.v11i4.5151))
19. Bhavaneetharan, L. (2025, February). A comprehensive review of bias detection and XAI techniques in NLP. In 2025 5th International Conference on Advanced Research in Computing (ICARC) (pp. 1–6). IEEE. ([https://doi.org/10.1109/ICARC64760.2025.10962966](https://doi.org/10.1109/ICARC64760.2025.10962966))
20. Braun, V., & Clarke, V. (2024). Supporting best practice in reflexive thematic analysis reporting in palliative medicine: A review of published research and introduction to the Reflexive Thematic Analysis Reporting Guidelines (RTARG). Palliative Medicine, 38(6), 608–616. ([https://doi.org/10.1177/02692163241234800](https://doi.org/10.1177/02692163241234800))
21. Creswell, J. W., & Inoue, M. (2025). A process for conducting mixed methods data analysis. Journal of General and Family Medicine, 26(1), 4–11. ([https://doi.org/10.1002/jgf2.736](https://doi.org/10.1002/jgf2.736))
22. Das, A., & Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (XAI): A survey. arXiv preprint arXiv:2006.11371. ([https://doi.org/10.48550/arXiv.2006.11371](https://doi.org/10.48550/arXiv.2006.11371))
23. Deppe, C., & Schaal, G. S. (2024). Cognitive warfare: A conceptual analysis of the NATO ACT cognitive warfare exploratory concept. Frontiers in Big Data, 7, 1452129. ([https://doi.org/10.3389/fdata.2024.1452129](https://doi.org/10.3389/fdata.2024.1452129))
24. Dwivedi, R., et al. (2023). Explainable AI (XAI): Core ideas, techniques, and solutions. ACM Computing Surveys, 55(9), 1–33. ([https://doi.org/10.1145/3561048](https://doi.org/10.1145/3561048))
25. Ennab, M., & Mcheick, H. (2025). Advancing AI interpretability in medical imaging: A comparative analysis of pixel-level interpretability and Grad-CAM models. Machine Learning and Knowledge Extraction, 7(1), 12. ([https://doi.org/10.3390/make7010012](https://doi.org/10.3390/make7010012))
26. Fenstermacher, L., Uzcha, D., Larson, K., Vitiello, C., & Shellman, S. (2023, June). New perspectives on cognitive warfare. In Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII (Vol. 12547, pp. 172–187). SPIE. ([https://doi.org/10.1117/12.2666777](https://doi.org/10.1117/12.2666777))
27. Gunning, D., & Aha, D. (2019). DARPA’s explainable artificial intelligence (XAI) program. AI Magazine, 40(2), 44–58. ([https://doi.org/10.1609/aimag.v40i2.2850](https://doi.org/10.1609/aimag.v40i2.2850))
28. Islam, S. R., Eberle, W., Ghafoor, S. K., & Ahmed, M. (2021). Explainable artificial intelligence approaches: A survey. arXiv preprint arXiv:2101.09429. ([https://doi.org/10.48550/arXiv.2101.09429](https://doi.org/10.48550/arXiv.2101.09429))
29. Machlev, R., et al. (2022). Explainable artificial intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities. Energy and AI, 9, 100169. ([http://dx.doi.org/10.1016/j.egyai.2022.100169](http://dx.doi.org/10.1016/j.egyai.2022.100169))
30. Mustafa, A. M., et al. (2024). Interpreting Arabic transformer models: A study on XAI interpretability for Qur’anic semantic-search models. Jordanian Journal of Computing and Information Technology, 10. ([https://doi.org/10.5455/jjcit.71-1704878720](https://doi.org/10.5455/jjcit.71-1704878720))
31. Shafie, R. S., et al. (2024). Psychosemantics of “Us” and “Them” in social media warfare. SEARCH Journal of Media and Communication Research, 16(2), 65–81. ([http://dx.doi.org/10.58946/search-16.2.P5](http://dx.doi.org/10.58946/search-16.2.P5))
32. Stanek, D., Klaban, I., & Coufalíková, A. (2025, May). Explainable artificial intelligence: State of the art and beyond. In 2025 International Conference on Military Technologies (ICMT) (pp. 1–7). IEEE. ([https://ieeexplore.ieee.org/document/11005246](https://ieeexplore.ieee.org/document/11005246))
33. Zhang, H., & Ogasawara, K. (2023). Grad-CAM-based explainable artificial intelligence related to medical text processing. Bioengineering, 10(9), 1070. ([https://doi.org/10.3390/bioengineering10091070](https://doi.org/10.3390/bioengineering10091070))
 
Digital Islamic Humanities
Volume 1, Issue 1
September 2025
Pages 311-354