An Analysis of the Content in Social Networks During COVID-19 Pandemic

During the COVID-19 pandemic, Internet and SN technologies are an effective resource for disease surveillance and a good way to communicate to prevent disease outbreaks. In December 2019, the frequency of the words COVID-19, SARS-CoV-2, and pandemic was very low in online environment, being only few posts informing that, "the mysterious coronavirus in China could spread." After March 1, 2020, there have been numerous research projects that analyze the flows of messages in social networks in order to perform real-time analyses, to follow the trends of the pandemic evolution, to identify new disease outbreaks, and to elaborate better predictions. In this context, this study analyzes the posts collected during [August-September 2020], on the Twitter network, that contain the word "COVID-19," written both in Romanian and English. For the Romanian language posts, we obtained a dictionary of the words used, for which it was calculated their occurrence frequency in the multitude of tweets collected and pre-processed. The frequency of words for non-noisy messages was identified from the multitude of words in the obtained dictionary. For the equivalent of these words in English, we obtained the probability density of words in the extracted and pre-processed posts written in English on Twitter. This study also identifies the percentage of similarity between tweets that contain words with a high frequency of apparition. The similarity for the collected and pre-processed tweets that have "ro." in the filed called Language has been computed making use of Levenshtein algorithm. These calculations are intended to quickly help find the relevant posts related to the situation generated by the COVID-19 pandemic. It is well known that the costs of analyzing data from social networks are very low compared to the costs involved in analyzing data from the centers of government agencies; therefore, the proposed method may be useful.