A Classification of Quran Verses Using Deep Learning

Abstract

Understanding the topics of Quran verses is considered as a main interest of Islamic Scholars, specialists of Quran studies and others. The traditional classification of Quran verses can be simplified and improved using the automated techniques such as Natural Language Processing (NLP) and Machine Learning (ML). While the majority of the current studies have used traditional ML approaches with small datasets, we used the Deep Learning (DL) algorithms with larger dataset for classifying Quran verses. This paper proposes a method for multi-label classification for accurately classifying Quran verses based on 12 predefined main topics using DL. We designed a structured method that consists of multiple steps for achieving the objective of this study. Firstly, a dataset of labeled Quran verses is collected, organized and converted to sequences of numbers to be understood by the DL models. The skip-gram algorithm of Word2Vec is used for considering the semantic of text to improve the models’ performances. Then the embedding vectors are fed to two different DL models which are RNN and CNN to classify verses. The results of DL classifiers are evaluated based on accuracy, precision, recall, F1-score, and hamming loss where the cross-validation technique is used for more accurate results. The values of 90.41%, 96.98%, 92.40%, 93.81% and 0.0126 for accuracy, precision, recall, F1-score and hamming loss respectively were achieved as best results. The findings of this study help specialists of Quran studies to gain more insight for easier studying and teaching the topics discussed by Quran verses.