An ""Infodemic"": Leveraging High-Volume Twitter Data to Understand Public Sentiment for the COVID-19 Outbreak

Richard J. Medford; Sameh N. Saleh; Andrew Sumarsono; Trish M. Perl; Christoph U. Lehmann

From January 14 th to 28 th 2020, a random sample of tweets in the English language was extracted using Twitter's API and its advanced search tool (https://twitter.com/search-advanced). The Twitter stream was filtered in accordance with Twitter's advanced search algorithm resulting in a representative subset of tweets. The dates were chosen to include one week of data before and after the activation of the Emergency Operations Center by the Centers for Disease Control and Prevention [13] and the release of the first WHO situation report [14] . Hashtags used for identification of 2019-nCoV related tweets included #2019nCoV, #coronavirus, #nCoV2019, #wuhancoronavirus, and #wuhanvirus (COVID-19 and SARS-COV-2 were not coined until Feb 19, 2020). Collected metadata from tweets included nineteen variables, of which eight were used in our analysis: tweet text, time stamp, if the tweet had a reply, if the tweet was a reply, if the tweet was unique or a retweet, if the tweet included an image, if the tweet included a link, the number of tweet likes, number of retweets, and number of replies.