Arabic Quran Verses Authentication Using Deep Learning and Word Embeddings

The international arab journal of information technology

article

Zineb Touati-Hamad¹  Issam Bendib¹  Saqib Hakak² 

[1] Laboratory of Mathematics, Informatics and Systems, University Larbi Tebessi;Faculty of Computer Science, University of New Brunswick

关键词: Arabic text;    Quranic verse;    Authentication;    NLP;    Word Embeddings;    Word2vec;    DL;    CNN;    LSTM;   

DOI  :  10.34028/iajit/19/4/13

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

Nowadays, with the developments witnessed by the Internet, algorithms have come to control all aspects of digitalcontent. Due to its Arabic roots, it is ironic to find that Arabic Quranic content is still thirsty to benefit from computerlinguistics, especially with the advent of artificial intelligence algorithms. The massive spread of Islamic-typed websites andapplications has led to a widespread of digital Quranic content. Unfortunately, such content lacks censorship and can rarelymatch resourcefulness. It is quite difficult, especially for a non-native speaker of the Arabic language, to distinguish andauthenticate the provided Quranic verses from the non-Quranic Arabic texts. Text processing techniques classified outside thefield of Natural Language Processing (NLP) give less qualified results, especially with Arabic texts. To address this problem,we propose to explore Word Embeddings (WE) with Deep Learning (DL) techniques to identify Quranic verses in Arabictextual content. The proposed work is evaluated using twelve different word embeddings models with two popular classifiersfor binary classification, namely: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). Theexperimental results showed the superiority of the proposed approach over traditional methods in distinguishing between theQuranic verses and the Arabic text with an accuracy of 98.33%.

【 授权许可】

Unknown