Datasets for Tweets from Anonymous Physicians about COVID-19 in the U.S.

This dataset was created for a project that assessed Twitter data from physicians posted anonymously by administrators of a specific Twitter user page to better understand physician perspectives and sentiments about COVID-19 in the United States. 

Tweet identifiers are contained in the 'tweet_identifiers.csv file'

Other files contain sentiment analysis data; one file used vaderSentiment in Python 3, and the other file used NRC in R (see sources below for further information and use of these packages.

Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.

NRC Emotion Lexicon, Saif M. Mohammad and Peter D. Turney, NRC Technical Report, December 2013, Ottawa, Canada.

Jockers ML (2015). Syuzhet: Extract Sentiment and Plot Arcs from Text. https://github.com/mjockers/syuzhet.

Code used specifically for this project may be found at: https://github.com/sullkath/tweet_analysis

Link to paper publication: 

Pre-print in bioRxiv available at: