Computational methodologies for sanad-based hadith analysis: a review

Abstract

Hadith literature, a cornerstone of Islamic tradition, critically depends on the sanad (chain of narrators) for authentication, a process traditionally requiring profound scholarly expertise. This paper presents a systematic review of computational methodologies designed to enhance and automate sanad analysis, bridging Islamic studies with advanced artificial intelligence (AI). We categorize progress across four key domains: automated authenticity classification, sophisticated narrator network analysis, textual information extraction (e.g., named entity recognition), and the development of specialized datasets and ontologies. Our findings reveal a significant paradigm shift from rule-based systems to advanced machine learning (ML) and deep learning (DL) techniques. This review synthesizes contributions from over 50 studies, highlighting critical challenges including data scarcity, narrator disambiguation, and cross-linguistic resource limitations. We emphasize the novelty of this cross-domain synthesis and discuss how these intelligent systems can be integrated into digital Islamic archives, low-resource mobile hadith applications, and embedded natural language processing (NLP) engines. This work charts a course for future research to develop more robust, scalable, and ethically grounded computational tools, complementing traditional hadith scholarship with advanced engineering solutions