This study analyzed over 105 million tweets and Weibo messages from March 1 to May 15, 2020, across six languages (English, Spanish, Arabic, French, Italian, and Chinese), to examine the emotional landscape of the COVID-19 pandemic. Using deep learning models, the researchers identified various emotional expressions (positive, negative, and joking). The analysis revealed a rapid rise and slow decline in conversation volume, triggered by economic collapse and confinement measures. Similar emotional patterns emerged across languages, with a mix of joking and negative emotions initially, followed by an increase in positive emotions as the pandemic subsided.
Publisher
Humanities & Social Sciences Communications
Published On
May 17, 2021
Authors
Xiangliang Zhang, Qiang Yang, Somayah Albaradei, Xiaoting Lyu, Hind Alamro, Adil Salhi, Changsheng Ma, Manal Alshehri, Inji Ibrahim Jaber, Faroug Tifratene, Wei Wang, Takashi Gojobori, Carlos M. Duarte, Xin Gao
Tags
COVID-19
emotional landscape
tweets
Weibo
deep learning
multilingual analysis
pandemic
Related Publications
Explore these studies to deepen your understanding of the subject.
