Knowledge Discovery in the Hadith According to the Reliability and Memory of the Reporters Using Machine Learning Techniques

Hammam M. Abdelaal,Abdelmoty M. Ahmed,Hassan A. Youness Alansary,Wade Ghribi

doi:10.1109/access.2019.2944118

Hammam M. Abdelaal, Abdelmoty M. Ahmed + Show 2 more

Open Access

https://doi.org/10.1109/access.2019.2944118

Copy DOI

Abstract

Muslims suffer from not knowing the validity of the Hadiths or verification of its degree, which represented the second source of legislation in Islam after the Quran. Although many sites allow users in general and Muslims, in particular, the possibility of verifying the authenticity of the hadith, but it is through an information system which is connected to the database of the Hadith. So, there is no intelligent system that can distinguish the hadith automatically, therefore, in this study, we propose a model that can recognize and categorize the hadith automatically and conclusion the essential features through Hadith classification into Sahih, Hasan, Da’if, and Maudu, based on machine learning techniques. This study is primarily concerned with classifying the hadith according to the memory and reliability of the Hadith’s narrators. This classification does not depend only on the text of the hadith, as in the rest of the other Arab documents, but depend on also the Sanad of Hadith. Therefore, this study was conducted on three methodologies; these methodologies help us to obtain an accuracy that is more reliable for hadith classification compared to previous researches in this area. In addition to building a model using the Decision tree technique based on the Sanad of hadith for helping us deciding to judge the validity of the hadith, the accuracy of this classifier reached up to 92.59%. Several Learning algorithms have been used in this study, but we reported the best three classifiers (LinearSVC, SGDClassifier, and Logistic regression), which achieved higher accuracy reached up to 93.69%, 93.51, and 92.27% respectively.

Highlights

Text classification is a task of data mining; it aims to assign automatically selected documents into categories from a pre-defined set of classes [2]
Each algorithm is tested using crossvalidation method, that the best method to evaluate the algorithm as the previous that mentioned before in section 1 [28], [32] We note from the experiments results that the accuracy of the classification of hadith according to what was attributed to the Prophet is better than the results of classification of the hadith according to the reliability and memory of the reporters, because the first classification only depends on the text of hadith that contains some features and keywords that distinguishing each class, ; there is a relationship between the content of hadith text and its class
The Experimental results revealed that adding the Sanad of hadith to the text in the classification process have a significant impact on the increase the classification accuracy because this classification depends on the Sanad of hadith, which identifying and evaluating the hadith degree

Summary

Introduction

Text classification is a task of data mining; it aims to assign automatically selected documents into categories from a pre-defined set of classes [2]. This task is usually solved by combining Information Retrieval and Machine Learning. Abdelaal et al.: Knowledge Discovery in the Hadith According to the Reliability and Memory of the Reporters techniques. The main goals of the paper are to classify the prophetic hadith into different categories according to the reliability and memory of the reporters, determine performance and efficiency of the categorization model, and try to get a relationship or correlation between hadith classifications

Objectives

Methods

Findings

Conclusion