Open Access

ARTICLE

Computational Linguistics Based Arabic Poem Classification and Dictarization Model

Manar Ahmed Hamza^1,*, Hala J. Alshahrani², Najm Alotaibi³, Mohamed K. Nour⁴, Mahmoud Othman⁵, Gouse Pasha Mohammed¹, Mohammed Rizwanullah¹, Mohamed I. Eldesouki⁶

1 Department of Computer and Self Development, Preparatory Year Deanship, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia
2 Department of Applied Linguistics, College of Languages, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
3 Prince Saud AlFaisal Institute for Diplomatic Studies, Riyadh, Saudi Arabia
4 Department of Computer Science, College of Computing and Information System, Umm Al-Qura University, Makkah, Saudi Arabia
5 Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo, 11835, Egypt
6 Department of Information System, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia

* Corresponding Author: Manar Ahmed Hamza. Email:

Computer Systems Science and Engineering 2024, 48(1), 97-114. https://doi.org/10.32604/csse.2023.034520

Received 19 July 2022; Accepted 13 November 2022; Issue published 26 January 2024

Abstract

Computational linguistics is the scientific and engineering discipline related to comprehending written and spoken language from a computational perspective and building artefacts that effectively process and produce language, either in bulk or in a dialogue setting. This paper develops a Chaotic Bird Swarm Optimization with deep ensemble learning based Arabic poem classification and dictarization (CBSOEDL-APCD) technique. The presented CBSOEDL-APCD technique involves the classification and dictarization of Arabic text into Arabic poetries and prose. Primarily, the CBSOEDL-APCD technique carries out data pre-processing to convert it into a useful format. Besides, the ensemble deep learning (EDL) model comprising deep belief network (DBN), gated recurrent unit (GRU), and probabilistic neural network (PNN) are exploited. At last, the CBSO algorithm is employed for the optimal hyperparameter tuning of the deep learning (DL) models to enhance the overall classification performance. A wide range of experiments was performed to establish the enhanced outcomes of the CBSOEDL-APCD technique. Comparative experimental analysis indicates the better outcomes of the CBSOEDL-APCD technique over other recent approaches.

---

Keywords

---