A Multi-Label Classification on Topics of Quranic Verses in English Translation Using Tree Augmented Naïve Bayes

Abstract

Quran is an eternal miracle for depicting its linguistic perfection, truth, and validating of the latest scientific research. Every Muslims must conceive and implement the commandments, also avoid the prohibitions mentioned in the Quran. Each verse of the Quran has a different meaning, and one verse in the Quran can depict one or more topics of class that can be studied. To ease learning and to understand the verses of Quran, each of them needs to be classified appropriately on its different topics. In this research, the model of classification was built that is able to identify the topics classes of each verse of Quran by multi-label classification approach. The model was built using Tree Augmented Naive Bayes (TAN). In order to improve performance, Mutual Information (MI) is employed to select dependent variables. The results show that the classification model built using TAN with MI obtained best performance with average Hamming Loss of 0.1121, while the model built using TAN without MI obtained average Hamming Loss of 0.1208.