An evolutionary clustering analysis of the social media content and global infection rate during the COVID-19 pandemic (Preprint)
BACKGROUND COVID-19 has not only psychological but also economic and social effects and social media increased the negative effects by disseminating COVID-19 infodemic. OBJECTIVE This study aims to investigate impact of the global infection rate on social media posting during the COVID-19 pandemic. METHODS The study analyzed 179+ million tweets collected between March 22nd and April 13th, 2020, and global COVID-19 infection rate by using evolutionary clustering analysis. RESULTS The results indicated six clusters constructed for each term type, including three-level n-grams (unigrams, bigrams, and trigrams). The frequent occurrences of unigrams (“COVID-19”, “virus”, “government”, “people”, etc.), bigrams (“COVID-19”, “COVID-19 cases”, “times share”, etc.), and trigrams (“COVID 19 crisis”, “things help stop”, “trying times share”). The results demonstrated that the unigram trends on Twitter were up to about two times and 54 times more common than bigram and trigram terms, respectively. Unigrams like “home” or “need” also became important as these terms reflected the main concerns of people during this period. Taken together, the present findings confirm that many tweets were used to broadcast people’s prevalent topics of interest during the COVID-19 pandemic. Further, the results indicated that the number of COVID-19 infections has a significant impact on all clusters, being strong on 86% of clusters and moderate on 16% of clusters. The downward slope in the global infection rate reflected the start of the trending of “social distancing” and “stay at home.” CONCLUSIONS These findings suggested that infection rates have a significant impact on social media postings during the COVID-19 pandemic.