Evolution of COVID-19 tweets about Southeast Asian Countries: topic modelling and sentiment analyses

Abstract

Despite the global scale of this pandemic, comparison and contrast of topics, sentiment and emotions of tweets among countries are limited. Further, most previous studies covered a short timeframe due to the recency of the event and the large volume of tweets. The purposes of this research were to (1) identify the multiplicity of public discourse about countries during the COVID-19 pandemic and how they evolved, (2) compare and contrast sentiment levels and (3) compare emotions about countries over time. The research scope covered 115,553 tweets that mentioned ten countries in Southeast Asia (SEA) from 22 January 2020 to 31 July 2021. This research presents the infoveillance methods—using a topic modelling algorithm (LDA), VADER and NRC sentiment analyses—that elucidated the evolution and the emergence of public narratives and sentiment affecting country brands during the pandemic. Results also shed light on the role of word-of-mouth (WOM) communications in the place branding process.