Samuel, J.; Ali, G.G.M.N.; Rahman, M.M.; Esawi, E.; Samuel, Y. COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification. Information 2020, 11, 314.

University of Michigan - Ann Arbor

Google

- There has been mass fear and panic phenomena due to incomplete and often inaccurate information. 
 - There is a need to address and better understand COVID-19's informational crisis and gauge public sentiment, so that appropriate messaging and policy decisions can be implemented. 
- In the article, "COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification" by Jim Samuel  research article, public sentiment associated with the pandemic using Coronavirus specific Tweets and R statistical software, along with its sentiment analysis packages are identified. 
-  There have been insights into the progress of fear-sentiment over time as COVID-19 approached peak levels in the United States. 
The article uses descriptive textual analytics supported by necessary textual data visualizations. 
- Furthermore,  the article shows a methodological overview of two essential machine learning classification methods, in the context of textual analytics, and compares their effectiveness in classifying Coronavirus Tweets of varying lengths. 
- Samuel observes a strong classification accuracy of 91% for short Tweets, with the Naive Bayes method.
- There is also an observation made that the logistic regression classification method provides a reasonable accuracy of 74% with shorter Tweets, and both methods showed relatively weaker performance for longer Tweets. 
- The research provides insights into Coronavirus fear sentiment progression, and outlines associated methods, implications, limitations and opportunities.

Learn Before

Related