A Multi-Lable Classification on Topics of Quranic Verses in English Translation Using Multinomial Naive Bayes

Abstract

Al-Quran is the holy book as well as guidance for Muslims around the world. Each verse of Quran contains meaning and wisdom that can usually be classified into more than one topic of discussion. This research was conducted on the issue of classification of Quranic verses that can be classified into more than one topic as a multi-label classification problem. Multi-label classification is different from single-label classification, therefore this research provided a new model of classifier to handle multi-label classification. The system was developed using Multinomial Naïve Bayes with several stages of preprocessing data such as case folding, tokenization, and stemming. The system also used bag of words as feature extraction method. The best Hamming loss obtained from this research is 0.1247.