Classification of Hadith Topic of Indonesian Translation Using K-Nearest Neighbor and Chi-Square

Ghinaa Zain Nabiilah,Said Al Faraby,Mahendra Dwifebri Purbolaksono

doi:10.21108/ijoict.v7i2.573

Abstract

Hadith is the main way of life for Muslims besides the Qur'an whose can be applied in everyday life. Hadith also contains all the words or deeds of the Prophet Muhammad which are used as a source of the law of Islam. Therefore, many readers, especially Muslims, are interested in studying hadith. However, the large number of hadiths makes it difficult for readers or those who are still unfamiliar with Islam to read them. Therefore, we conducted a study to classify hadith textually based on the type of teaching, so that readers can get an overview or other reference in reading and searching for hadith based on the type of teaching more easily. This study uses KNN and chi-square methods as feature selection. We also carried out several test scenarios, including implementing stopword removal modifications in preprocessing and experimenting with selecting k values for KNN to determine the best performance. The best performance was obtained by using the value of k = 7 on KNN without implementing chi-square and with stopword removal modification with a hammer loss value of 0.1042 or about 89.58% of the data correctly classified.

Highlights

HADITH is something that comes from the Prophet Muhammad in the form of words, deeds, or approval and serves as an explanation and strengthening of the meaning of the content of the verses of the Qur'an so that its position in Islam is the source of basic law [1]
Several tests were carried out such as the first test, namely at the preprocessing stage by looking at the effect of using stopword removal, the test was at the feature selection stage, namely by looking at the effect of the large number of features used on the chi-square, the test was at the classification stage, namely by looking at the effect of selecting k on the accuracy results
K-Nearest Neighbor (KNN) multi-label classification using Sahih Bukhari Hadith data Indonesian translation with the chi-square feature selection method which has been described in the test scenario section has been successfully built with performance for each number of k selected in the KNN algorithm having an overall hamming loss value of each number k is not more than 0.1171 or correctly classified data is around 88.29%, and the most optimal hamming loss value is to use the number of k in KNN as much as 7

Summary

Introduction

HADITH is something that comes from the Prophet Muhammad in the form of words, deeds, or approval and serves as an explanation and strengthening of the meaning of the content of the verses of the Qur'an so that its position in Islam is the source of basic law [1]. The teachings contained in the hadith are something interesting to learn because they can apply in everyday life. These teachings can be grouped textually into several types such as recommendations, prohibitions, and information. We need a system that can classify hadith based on the type of teaching so that readers get imagine or other references in reading and looking for hadiths that contain suggestions, prohibitions, and information easier. In this research, multi-label classification to classify hadith according to the group of teachings such as recommendations, prohibitions, information, a combination of the two, or a combination of the three. The KNN method has been widely used because of its implementation simplicity and excellent performance

Objectives

Methods

Results

Conclusion