A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification

Arabic poetry follows intricate rhythmic patterns known as ‘arūḍ’ (prosody), which makes its automated categorization particularly challenging. While earlier studies primarily relied on conventional machine learning and recurrent neural networks, this work evaluates the effectiveness of transformer-...

Full description

Saved in:
Bibliographic Details
Main Authors: A. M. Mutawa, Sai Sruthi
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4941
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155888717856768
author A. M. Mutawa
Sai Sruthi
author_facet A. M. Mutawa
Sai Sruthi
author_sort A. M. Mutawa
collection DOAJ
description Arabic poetry follows intricate rhythmic patterns known as ‘arūḍ’ (prosody), which makes its automated categorization particularly challenging. While earlier studies primarily relied on conventional machine learning and recurrent neural networks, this work evaluates the effectiveness of transformer-based models—an area not extensively explored for this task. We investigate several pretrained transformer models, including Arabic Bidirectional Encoder Representations from Transformers (Arabic-BERT), BERT base Arabic (AraBERT), Arabic Efficiently Learning an Encoder that Classifies Token Replacements Accurately (AraELECTRA), Computational Approaches to Modeling Arabic BERT (CAMeLBERT), Multi-dialect Arabic BERT (MARBERT), and Modern Arabic BERT (ARBERT), alongside deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU). This study uses half-verse data across 14 m. The CAMeLBERT model achieved the highest performance, with an accuracy of 90.62% and an F1-score of 0.91, outperforming other models. We further analyze feature significance and model behavior using the Local Interpretable Model-Agnostic Explanations (LIME) interpretability technique. The LIME-based analysis highlights key linguistic features that most influence model predictions. These findings demonstrate the strengths and limitations of each method and pave the way for further advancements in Arabic poetry analysis using deep learning.
format Article
id doaj-art-418358a9dfd8453ab0f953d4e90bdc8f
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-418358a9dfd8453ab0f953d4e90bdc8f2025-08-20T02:24:44ZengMDPI AGApplied Sciences2076-34172025-04-01159494110.3390/app15094941A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter ClassificationA. M. Mutawa0Sai Sruthi1Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Safat 13060, KuwaitComputer Engineering Department, College of Engineering and Petroleum, Kuwait University, Safat 13060, KuwaitArabic poetry follows intricate rhythmic patterns known as ‘arūḍ’ (prosody), which makes its automated categorization particularly challenging. While earlier studies primarily relied on conventional machine learning and recurrent neural networks, this work evaluates the effectiveness of transformer-based models—an area not extensively explored for this task. We investigate several pretrained transformer models, including Arabic Bidirectional Encoder Representations from Transformers (Arabic-BERT), BERT base Arabic (AraBERT), Arabic Efficiently Learning an Encoder that Classifies Token Replacements Accurately (AraELECTRA), Computational Approaches to Modeling Arabic BERT (CAMeLBERT), Multi-dialect Arabic BERT (MARBERT), and Modern Arabic BERT (ARBERT), alongside deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU). This study uses half-verse data across 14 m. The CAMeLBERT model achieved the highest performance, with an accuracy of 90.62% and an F1-score of 0.91, outperforming other models. We further analyze feature significance and model behavior using the Local Interpretable Model-Agnostic Explanations (LIME) interpretability technique. The LIME-based analysis highlights key linguistic features that most influence model predictions. These findings demonstrate the strengths and limitations of each method and pave the way for further advancements in Arabic poetry analysis using deep learning.https://www.mdpi.com/2076-3417/15/9/4941Arabic poetryBERTdeep learningLIMEnatural language processingtransformer models
spellingShingle A. M. Mutawa
Sai Sruthi
A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
Applied Sciences
Arabic poetry
BERT
deep learning
LIME
natural language processing
transformer models
title A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
title_full A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
title_fullStr A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
title_full_unstemmed A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
title_short A Comparative Evaluation of Transformers and Deep Learning Models for Arabic Meter Classification
title_sort comparative evaluation of transformers and deep learning models for arabic meter classification
topic Arabic poetry
BERT
deep learning
LIME
natural language processing
transformer models
url https://www.mdpi.com/2076-3417/15/9/4941
work_keys_str_mv AT ammutawa acomparativeevaluationoftransformersanddeeplearningmodelsforarabicmeterclassification
AT saisruthi acomparativeevaluationoftransformersanddeeplearningmodelsforarabicmeterclassification
AT ammutawa comparativeevaluationoftransformersanddeeplearningmodelsforarabicmeterclassification
AT saisruthi comparativeevaluationoftransformersanddeeplearningmodelsforarabicmeterclassification