MODELING OF ENHANCED FRACTAL CHEETAH OPTIMIZER WITH DEEP LEARNING FOR INTEGRATED ARABIC DIALECT IDENTIFICATION

Saad Alahmari, Najla I. Al-Shathry, Majdy M. Eltahir, Nuha Alruwais, Ahmed Sayed and Sitelbanat Abdelbagi
Additional contact information
Saad Alahmari: Department of Computer Science, Applied College, Northern Border University, Arar 91431, Saudi Arabia
Najla I. Al-Shathry: ��Department of Language Preparation, Arabic Language Teaching Institute, 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
Nuha Alruwais: �Department of Computer Science and Engineering, College of Applied Studies and Community Services, King Saud University, Saudi Arabia, P. O. Box 22459, Riyadh 11495, Saudi Arabia
Ahmed Sayed: �Research Center, Future University in Egypt, New Cairo 11835, Egypt
Sitelbanat Abdelbagi: ��Department of Computer and Self Development, Preparatory Year Deanship, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia

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

Abstract: The Arabic language has different variants that can roughly be classified into three major types, namely Modern Standard Arabic (MSA), Dialectal Arabic (DA), and Classical Arabic (CA). There are slight variations between CA and MSA regarding pronunciation, syntax, and terminology. On the other hand, DA is quite different from MSA and CA in that it reflects the country of origin, or at least the geographic location of the speaker if the mobility factor is considered. Deep learning demonstrated its effectiveness in DA detection tasks, leveraging neural network models such as transformer models, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Researchers have established models that automatically discriminate between Arabic dialects by processing contextual information, linguistic features, and phonetic patterns embedded in large datasets. Using Deep Learning (DL) in Arabic dialect detection contributes in various complex systems to the development of natural language processing. It assists in addressing the problems related to a wide variety of Arabic dialects, which facilitate applications including machine translation, speech recognition, and sentimental analysis tailored to regional linguistic variation. This study suggests an Enhanced Fractal Cheetah Optimization Algorithm with Deep Learning for Integrated Arabic Dialect Identification (ECOADL-IADI) technique. The ECOADL-IADI technique mainly intends to classify the variations of the Arabic language into multiple classes. At the preliminary level, the ECOADL-IADI technique performs preprocessing of Arabic text. Next, the BERT word embedding process is carried out. The ECOADL-IADI technique applies a Bidirectional Recurrent Neural Network (BiRNN) model for Arabic dialect identification. Lastly, the ECOA-based hyperparameter selection process improves the classifier outcomes of the BiRNN model. A wide range of experiments were conducted to examine the detection results of the ECODL-IADI technique. The extensive results stated that the ECODL-IADI technique performs well compared to other models.

Keywords: Arabic Dialect Identification; Natural Language Processing; Cheetah Optimization Algorithm; Modern Standard Arabic; Deep Learning (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/S0218348X25400389
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:s0218348x25400389

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0218348X25400389

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 ().