Qur’anic Verse Recommender System Using Hybrid SBERT-TFIDF Embedding and LLM-Based Explanation Facility
Muhammad Hermawan, Z. K. A. Baizal · 2025
Qur’anic verse recommender systems are increasingly needed to assist users in understanding the vast and profound contents of the Qur’an through natural language queries. With over 6,000 verses, identifying spiritually relevant content remains a challenge, especially for users who are not familiar with specific keywords, themes, or Arabic vocabulary. This paper proposes a novel hybrid embedding-based recommendation approach that combines Sentence-BERT (SBERT) for semantic sentence-level representation and Term Frequency–Inverse Document Frequency (TF-IDF) for keyword emphasis. This dual embedding strategy allows the system to better understand users’ explicit intents as well as the underlying semantic context of the queries, offering more accurate and meaningful verse suggestions. Unlike traditional recommender systems, this solution does not rely on user history or collaborative filtering, effectively addressing the cold-start problem. The system also integrates a Large Language Model (LLM), specifically LLaMA, to generate contextual and spiritually meaningful explanations in Bahasa Indonesia. These explanations are created using zero-shot prompting, enabling dynamic interpretation of the recommended verses based on the user's query context. The system is deployed via a Telegram bot, enabling broad accessibility and ease of use. Evaluations were conducted through expert review and user testing. Experts rated the relevance and quality of the recommendations with an average precision of 82.4%, while general users provided an average satisfaction rating of 4.37 out of 5 across various dimensions including ease of use, clarity, and relevance. This study contributes to the development of AI-driven religious tools by presenting a method that combines semantic embeddings and LLM-generated explanations for intuitive and reflective interaction with the Qur’anic text. It also demonstrates the potential of hybrid NLP approaches and conversational interfaces in enhancing spiritual learning and access to religious knowledge in the digital age.