COMPUTATIONAL INSIGHTS INTO ARABIC PROPAGANDA: AN INTEGRATION OF CORPUS LINGUISTICS WITH DEEP LEARNING APPROACH

Muhammad Swaileh A. Alzaidi, Faheed A. F. Alrslani, Alya Alshammari, Majdy M. Eltahir, Hanan Al Sultan and Ahmed S. Salama
Additional contact information
Muhammad Swaileh A. Alzaidi: Department of English Language, College of Language Sciences, King Saud University, P.O. Box 145111, Riyadh, Saudi Arabia
Faheed A. F. Alrslani: ��Department of Information Technology, Faculty of Computing and Information Technology, Northern Border University, Rafha, Saudi Arabia
Alya Alshammari: ��Department of Applied Linguistics, College of Languages, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
Majdy M. Eltahir: �Department of Information Systems, Applied College at Mahayil, King Khalid University, Abha, Saudi Arabia
Hanan Al Sultan: �Department of English, College of Arts, King Faisal University, Hofuf, Saudi Arabia
Ahmed S. Salama: ��Department of Electrical Engineering, Faculty of Engineering & Technology, Future University in Egypt, New Cairo 11845, Egypt

FRACTALS (fractals), 2025, vol. 33, issue 02, 1-15

Abstract: The Arab nation is seriously affected by computational propaganda. The detection of Arab computational propaganda has become a hot research topic in social networking platforms. Propaganda campaigns endeavor to influence people’s mindsets to improve a particular agenda. They automatically employ the anonymity of the Internet, the micro-profiling capability of social network platforms, and the ease of managing and creating coordinated networks to reach masses of social network users with persuasive messages, mainly aimed at topics each user is sensitive to, and ultimately affecting the outcomes on the targeted problem. Using computation techniques and methods, analysts and researchers can better understand the scope, scale, and impact of propaganda efforts in Arabic-speaking communities and develop strategies to counter them. In recent times, deep learning (DL) approaches targeted explicitly at analyzing, detecting, or countering propaganda within online platforms or Arabic-speaking communities. DL is a subset of machine learning (ML), which includes training artificial neural networks (ANNs) with multiple layers for learning data representation. This paper designs an improved fractal walrus optimization algorithm with DL-based Arab computation propaganda detection (IWOADL-ACPD) technique. The IWOADL-ACPD method mainly focuses on the recognition and classification of propaganda in the Arabic language. The IWOADL-ACPD method begins with a preprocessing step to standardize and clean raw Arabic text data. Consequently, BERT word embedding encodes meaningful data, capturing contextual nuances vital for accurately detecting propaganda. In addition, the stacked sparse autoencoder (SSAE) detection technique is employed to discern subtle patterns indicative of propaganda content. To improve the performance of the SSAE method, the IWOADL-ACPD method uses IWOA to fine-tune the hyperparameter effectively. The proposed IWOADL-ACPD method contributes to Arabic computation propaganda detection by providing an adaptive and comprehensive technique for the complexity of cultural, digital, and linguistic landscapes specific to the Arabic-speaking context. The robustness and efficacy of the IWOADL-ACPD technique are demonstrated through stimulation analysis on the Arabic dataset, which showcases its capability to perform better than other existing methods. The IWOADL-ACPD technique exhibited a superior accuracy value of 95.25% over existing methods.

Keywords: Arabic Language; Arab Computation Propaganda; Fractal Walrus Optimization Algorithm; Deep Learning; Social Media (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0218348X25400195
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:fracta:v:33:y:2025:i:02:n:s0218348x25400195

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0218348X25400195

Access Statistics for this article

FRACTALS (fractals) is currently edited by Tara Taylor

More articles in FRACTALS (fractals) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().