Sistem Tanya Jawab Konsultasi Shalat Berbasis RASA Natural Language Understanding (NLU)

Abstract

A chatbot is an intelligent system that provides users with direct interaction with machines via written media. This paper describes how to use chatbots to ask questions about prayer procedures. A Muslim sometimes has questions about the procedure for praying when he finds a difference between the procedures performed by other Muslims. In this case, the use of chatbots is to provide an explanation. This chatbot was developed using a deep learning model, especially LSTM, that was integrated with the RASA framework. LSTM (Long Short Term Memory) can efficiently save some of the needed memory while also removing some of the unnecessary memory. The Telegram platform was chosen for the chatbot's implementation. The results showed that the chatbot telegram prayer consultation with DIET Classifier and RASA was able to recognize questions and provide answers in the form of text and images, with 96 percent accuracy.