The Early Emotional Responses and Central Issues of People in the Epicenter of the COVID-19 Pandemic: An Analysis from Twitter Text Mining

ABSTRACT

This study aimed to explore citizens’ emotional responses and issues of interest in the context of the coronavirus disease 2019 (COVID-19) pandemic. The dataset comprised 65,313 tweets with the location marked as New York State. The data collection period was four days of tweets when New York City imposed a lockdown order due to an increase in confirmed cases. Data analysis was performed using R Studio. The emotional responses in tweets were analyzed using the Bing and NRC (National Research Council Canada) dictionaries. The tweets’central issue was identified by Text Network Analysis. When tweets were classified as either positive or negative, the negative sentiment was higher. Using the NRC dictionary, eight emotional classifications were devised “trust,” “fear,” “anticipation,” “sadness,” “anger,” “joy,” “surprise,” and “disgust.” These results indicated that citizens showed negative and trusting emotional reactions in the early days of the pandemic. Moreover, citizens showed a strong interest in overcoming and coping with other people such as social solidarity. Citizens were concerned about the confirmation of COVID-19 infection status and death. Efforts should be made to ensure citizens’ psychological stability by promptly informing them of the status of infectious disease management and the route of infection. © 2023, Tech Science Press. All rights reserved.