COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification

• DOI: 10.2139/ssrn.3584990
• Publication Date: 2020-05-04T12:00:32Z
• Authors: Jim Samuel; G. G. Md. Nawaz Ali; Md. Mokhlesur Rahman; Ek Esawi; Yana Samuel
• Keywords: FOS: Computer and information sciences; bepress|Engineering; PsyArXiv|Social and Behavioral Sciences|Social and Personality Psychology|Individual Differences; Information technology; 02 engineering and technology; Social and Behavioral Sciences; Computer Science - Information Retrieval; 0202 electrical engineering, electronic engineering, information engineering; PsyArXiv|Engineering Psychology; information_technology_data_management; PsyArXiv|Social and Behavioral Sciences|Social and Personality Psychology; Individual Differences; Social and Information Networks (cs.SI); COVID-19; Social and Personality Psychology; Computer Science - Social and Information Networks; Engineering Psychology; T58.5-58.64; textual analytics; 3. Good health; Coronavirus; PsyArXiv|Social and Behavioral Sciences; machine learning; sentiment analysis; bepress|Social and Behavioral Sciences; bepress|Social and Behavioral Sciences|Psychology|Social Psychology; bepress|Social and Behavioral Sciences|Psychology|Personality and Social Contexts; twitter; Information Retrieval (cs.IR)

Along with the Coronavirus pandemic, another crisis has manifested itself in the form of mass fear and panic phenomena, fuelled by incomplete and often inaccurate information. There is therefore a tremendous 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 this research article, we identify public sentiment associated with the pandemic using Coronavirus specific Tweets and R statistical software, along with its sentiment analysis packages. We demonstrate insights into the progress of fear-sentiment over time as COVID-19 approached peak levels in the United States, using descriptive textual analytics supported by necessary textual data visualizations. Furthermore, we provide a methodological overview of two essential machine learning classification methods, in the context of textual analytics, and compare their effectiveness in classifying Coronavirus Tweets of varying lengths. We observe a strong classification accuracy of 91% for short Tweets, with the Naive Bayes method. We also observe 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. This research provides insights into Coronavirus fear sentiment progression, and outlines associated methods, implications, limitations and opportunities.