Topic modelling and sentiment analysis during Covid-19 pandemic response: A systematic review

Abstract

The World Health Organization (WHO) has declared Covid-19 as a pandemic since March 11, 2020. The emergence of the Covid-19 pandemic has caused a lot of discussion around the world. Sentiment Analysis and Topic Modeling using Latent Dirichlet Allocation (LDA) can be used to extract patterns or information from a set of texts. This study uses a Systematic Literature Review (SLR) to see what the most dominant topics are discussed during the Covid-19 pandemic and find out research gaps for further research about Sentiment Analysis and Topic Modeling using Latent Dirichlet Allocation (LDA). The articles used are limited to the article publication period, February 2020 to July 2021. The results of the review show that case handling (lockdown, international airports closure), conspiracy issues and fake news, number of daily case reports, the importance of covid prevention, Covid-19 vaccination policy, economic downturn, transportation systems, learning systems, and new policies for each country were the most discussed topics from March 2020 to January 2021.