Search System for Translation of Al-Qur'an Verses in Indonesian using BM25 and Semantic Query Expansion

Abstract

Al-Qur'an is a source of life guidance for Muslims. The digital version of the Qur'an is already available on the android platform. The Indonesian Ministry of Religion provides an official application called the Ministry of Religion's Qur'an which has a translation search system in it. However, adjustments need to be made so that Indonesian people can look for translations of verses that have a definite order based on their level of relevance to the keywords entered. This study aims to develop a search system for translations of Indonesian-language Qur'an verses that already exist in the Ministry of Religion's Qur'an application.This study uses the BM25 algorithm with Word2vec as the Semantic Query Expansion method. Data as many as 6236 translated documents in the application are used to create a model of the search system. Tests on hyperparameters are carried out to get the most optimal model. The research results obtained several hyperparameter values in SQE including a window of 7, and a query expansion term of 1. In the BM25 hyperparameter, the optimal condition is obtained when the k1 variable is 1.8 and the b variable is 0.85. The search system was evaluated using the Mean Average Precision and compared with the search system that was previously available in the Ministry of Religion's Qur'an. The MAP score increased with the proposed method, from 0.53718 to 0.66556.