BERT based Named Entity Recognition for Automated Hadith Narrator Identification

Hadith serves as a second source of Islamic law for Muslims worldwide, especially in Indonesia, which has the world's most significant Muslim population 228.68 million people. However, not all texts have been certified and approved use, several falsified Hadiths make it challenging to distinguish between authentic fabricated Hadiths. In terms science, determining authenticity can be accomplished by examining its Sanad Matn. is an essential aspect because indicates chain Narrator who transmits Hadith. The research reported this paper provides advanced Natural Language Processing (NLP) technique identifying authenticating part Sanad, utilizing Named Entity Recognition (NER) address necessity NER described adds extra feed-forward classifier last layer pre-trained BERT model. testing process using Cahya/bert-base-indonesian-1.5G, proposed solution received overall F1-score 99.63 percent. On Identification other passages, final examination yielded 98.27 percent F1-score.