Predicting Frequently Asked Questions (FAQs) on the COVID-19 Chatbot using the DIET Classifier
Wistiani Astuti, Desy Pratiwi Ika Putri, Aji Prasetya Wibawa, Yulita Salim, Purnawansyah Purnawansyah, Anusua Ghosh
Abstract
A popular dialogue system in the field of natural language processing (NLP) is the chatbot. Chatbots aim to create conversations between humans and machines. COVID-19 is a member of the Coronavidae (CoV) family of the Corona viirinae family which causes the respiratory system to become severe in humans. This paper predicts chatbot answers to questions about COVID-19 with the RASA framework and uses the DIET Classifier pipeline for 300 training data. The test results with the DIET Classifier model on rasa.core.test and rasa.nlu.test provided confidence values of F1-Score, precision, and accuracy for the correct answer to the question about COVID-19, namely 1.0 with a percentage of around 85%.