JMIR Publications

ABSTRACT

The effectiveness of public health measures depends upon a community’s compliance, as well as on its positive or negative emotions. The purpose of this study was to perform an analysis of expressed emotions in Greek Twitter during the first flow of COVID-19. The study period was January 25th June 30th, 2020. The data collection was performed via the Twitter filter streaming API using appropriate search keywords. The emotional analysis of the tweets that satisfied the inclusion criteria was achieved using a deep learning approach (suggested by Colnerič and Demšar 2020) that performs better by utilizing recurrent neural networks on sequences of characters. Emotional epidemiology tools like the six basic emotions (joy, sadness, disgust, fear, surprise, and anger) based on the Paul Eckman classification were adopted. Surprise at the emerging contagion was the most frequent emotion detected, while the imposed isolation resulted mostly in anger (OR=2.108). Yet, Greeks felt rather safe during the first COVID-19 flow, while their positive and negative emotions reflected a masked “flight or fight” response to the epidemic contagion. The emotional analysis emerges as a valid tool for epidemiology evaluations, design and public health strategy and surveillance.