Azala

Boosting Arabic text classification using hybrid deep learning approach

Gorde:
Argitaratua izan da:SN Applied Sciences vol. 7, no. 6 (Jun 2025), p. 540
Argitaratua:
Springer Nature B.V.
Gaiak:
Arabic language
Text categorization
Internet
Datasets
Deep learning
Classification
Computer architecture
English language
Information retrieval
Language
Artificial neural networks
Long short-term memory
Machine learning
Accuracy
Sentiment analysis
Neural networks
Support vector machines
Recurrent neural networks
Natural language processing
Information processing
Algorithms
Hybrid systems
Decision trees
Large language models
Economic
Sarrera elektronikoa:Citation/Abstract
Full Text
Full Text - PDF
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
Laburpena:As a significant natural language processing task (NLP), Arabic text classification is essential for efficiently processing and analyzing Arabic language content in various digital forms, such as information retrieval, sentiment analysis, and topic modeling. Deep Learning architectures, such as convolutional neural networks (CNN) and long short-term memory (LSTM), have been widely utilized to categorize and organize language contents accurately to improve the autonomy and perception of NLP tasks. In this paper, we develop a hybrid deep learning framework for Arabic text classification, using the Inception-CNN (introduced in the GoogleNet architecture) and the LSTM (variation of the Recurrent Neural Network). Specifically, the proposed system has been trained and evaluated on two datasets of an Arabic articles dataset, viz. SANAD and NADiA datasets. Consequently, several variations of the model architecture have been configured, trained, evaluated, and compared, with the aim of obtaining the best model architecture and hyperparameters. Our best experimental evaluation showed that the proposed hybrid system (Inception CNN with and LSTM) yielded an accuracy of 92% and 96% for the Akhbarona and AlKhaleej datasets, respectively. At the same time, the entire SANAD data set also yielded a high accuracy of 92%. Lastly, comparing with the state-of-the-art models revealed the superiority of our hybrid model, which outperformed the other architectures in the same area of study, the accuracies have been improved by 1% to 30% for the different datasets.Article Highlights<list list-type="bullet"><list-item></list-item>Proposing a model that combines the Inception module (CNN architecture) and LSTM for Arabic Text Classification<list-item>Research conducted on a low-sourced language; Arabic, using the datasets SANAD and NADiA.</list-item><list-item>The proposed model has yielded an accuracy of 92% for SANAD and 89% for NADiA, which outperformed other compared architectures.</list-item>
ISSN:2523-3963
2523-3971
DOI:10.1007/s42452-025-07025-x
Baliabidea:Science Database