A Proposed Chatbot Framework for COVID-19

In recent years, chatbots have gained traction in a variety of fields, including health care, education, marketing, cultural heritage, support networks, entertainment, and many others. To manage the large number of user requests during pandemics, chatbots have become a must-have piece of equipment. In this paper, we present a smart chatbot system that can communicate with people and provide them with answers about the COVID-19. To tackle the popular role of question answering, our model used the pre-trained Google BERT language model. On top of the BERT, we add two architectural phases for the question-answering task. The first step is a text classification technique that employs the BERT Transformer to categorise text input into various categories based on the meaning of the words themselves. The actual application of the BERT model, as well as the query domain for answers, is the second step. Our proposed system is trained and tested on Stanford University’s SQuAD V2.0, a well-known question-answering dataset.