Classification of Holy Quran translation using Neural Network technique

Suhaib Kh Hamed, Mohd Juzaiddin Ab Aziz

Research output: Contribution to journalArticle

Abstract

The Holy Quran is the most significant religious text which is followed by the believers of the Islamic religion. The translations of the Quran are the interpretation of its meaning in different languages to assist those who are not familiar with the Arabic language. The Holy Quran consists of 114 Chapters (Surah) and 6236 Verses. These 114 Chapters have different length. The verse is the smallest segment of the texts of the Quran. The Holy Quran as a book is not classified on topics and its verses describe many topics and many verses even from different chapters converge within the same theme. The number of verses and chapters may share similar topics such as faith and morality. One of the solutions to tackle this issue is the Quran classification. Thus, the aim of this study is to classify the Quranic verses by using the Neural Network (NN) classifier based on the predefined topics in order to provide the readers the relevant Quranic verses depending on their need. This research used the most popular and the widespread of the Holy Quran translation in English language by Abdullah Yusuf Ali as the reference dataset. In this regard, the neural network classifier will address this issue through classifying the Al-Baqarah Surah that represents the Quran into two categories which are the Fasting and Pilgrimage topics. Finally, based on the F-measure, the evaluation of Al-Baqarah classification by using NN showed a level of approximately 90%. This proves that NN has succeeded in presenting a encouraging result in this critical area.

Original languageEnglish
Pages (from-to)4468-4475
Number of pages8
JournalJournal of Engineering and Applied Sciences
Volume13
Issue number12
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Neural networks
Classifiers

Keywords

  • Holy Quran
  • Information retrieval
  • Issue
  • Machine leaming
  • Neural network classification
  • Text

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Classification of Holy Quran translation using Neural Network technique. / Hamed, Suhaib Kh; Ab Aziz, Mohd Juzaiddin.

In: Journal of Engineering and Applied Sciences, Vol. 13, No. 12, 01.01.2018, p. 4468-4475.

Research output: Contribution to journalArticle

@article{5adfab7833134bcab089b91edae242fc,
title = "Classification of Holy Quran translation using Neural Network technique",
abstract = "The Holy Quran is the most significant religious text which is followed by the believers of the Islamic religion. The translations of the Quran are the interpretation of its meaning in different languages to assist those who are not familiar with the Arabic language. The Holy Quran consists of 114 Chapters (Surah) and 6236 Verses. These 114 Chapters have different length. The verse is the smallest segment of the texts of the Quran. The Holy Quran as a book is not classified on topics and its verses describe many topics and many verses even from different chapters converge within the same theme. The number of verses and chapters may share similar topics such as faith and morality. One of the solutions to tackle this issue is the Quran classification. Thus, the aim of this study is to classify the Quranic verses by using the Neural Network (NN) classifier based on the predefined topics in order to provide the readers the relevant Quranic verses depending on their need. This research used the most popular and the widespread of the Holy Quran translation in English language by Abdullah Yusuf Ali as the reference dataset. In this regard, the neural network classifier will address this issue through classifying the Al-Baqarah Surah that represents the Quran into two categories which are the Fasting and Pilgrimage topics. Finally, based on the F-measure, the evaluation of Al-Baqarah classification by using NN showed a level of approximately 90{\%}. This proves that NN has succeeded in presenting a encouraging result in this critical area.",
keywords = "Holy Quran, Information retrieval, Issue, Machine leaming, Neural network classification, Text",
author = "Hamed, {Suhaib Kh} and {Ab Aziz}, {Mohd Juzaiddin}",
year = "2018",
month = "1",
day = "1",
doi = "10.3923/jeasci.2018.4468.4475",
language = "English",
volume = "13",
pages = "4468--4475",
journal = "Journal of Engineering and Applied Sciences",
issn = "1816-949X",
publisher = "Medwell Journals",
number = "12",

}

TY - JOUR

T1 - Classification of Holy Quran translation using Neural Network technique

AU - Hamed, Suhaib Kh

AU - Ab Aziz, Mohd Juzaiddin

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The Holy Quran is the most significant religious text which is followed by the believers of the Islamic religion. The translations of the Quran are the interpretation of its meaning in different languages to assist those who are not familiar with the Arabic language. The Holy Quran consists of 114 Chapters (Surah) and 6236 Verses. These 114 Chapters have different length. The verse is the smallest segment of the texts of the Quran. The Holy Quran as a book is not classified on topics and its verses describe many topics and many verses even from different chapters converge within the same theme. The number of verses and chapters may share similar topics such as faith and morality. One of the solutions to tackle this issue is the Quran classification. Thus, the aim of this study is to classify the Quranic verses by using the Neural Network (NN) classifier based on the predefined topics in order to provide the readers the relevant Quranic verses depending on their need. This research used the most popular and the widespread of the Holy Quran translation in English language by Abdullah Yusuf Ali as the reference dataset. In this regard, the neural network classifier will address this issue through classifying the Al-Baqarah Surah that represents the Quran into two categories which are the Fasting and Pilgrimage topics. Finally, based on the F-measure, the evaluation of Al-Baqarah classification by using NN showed a level of approximately 90%. This proves that NN has succeeded in presenting a encouraging result in this critical area.

AB - The Holy Quran is the most significant religious text which is followed by the believers of the Islamic religion. The translations of the Quran are the interpretation of its meaning in different languages to assist those who are not familiar with the Arabic language. The Holy Quran consists of 114 Chapters (Surah) and 6236 Verses. These 114 Chapters have different length. The verse is the smallest segment of the texts of the Quran. The Holy Quran as a book is not classified on topics and its verses describe many topics and many verses even from different chapters converge within the same theme. The number of verses and chapters may share similar topics such as faith and morality. One of the solutions to tackle this issue is the Quran classification. Thus, the aim of this study is to classify the Quranic verses by using the Neural Network (NN) classifier based on the predefined topics in order to provide the readers the relevant Quranic verses depending on their need. This research used the most popular and the widespread of the Holy Quran translation in English language by Abdullah Yusuf Ali as the reference dataset. In this regard, the neural network classifier will address this issue through classifying the Al-Baqarah Surah that represents the Quran into two categories which are the Fasting and Pilgrimage topics. Finally, based on the F-measure, the evaluation of Al-Baqarah classification by using NN showed a level of approximately 90%. This proves that NN has succeeded in presenting a encouraging result in this critical area.

KW - Holy Quran

KW - Information retrieval

KW - Issue

KW - Machine leaming

KW - Neural network classification

KW - Text

UR - http://www.scopus.com/inward/record.url?scp=85055924339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055924339&partnerID=8YFLogxK

U2 - 10.3923/jeasci.2018.4468.4475

DO - 10.3923/jeasci.2018.4468.4475

M3 - Article

VL - 13

SP - 4468

EP - 4475

JO - Journal of Engineering and Applied Sciences

JF - Journal of Engineering and Applied Sciences

SN - 1816-949X

IS - 12

ER -