Abstract
As governments take measures against COVID-19, the epidemic situation is expected to improve, but public sentiment is likely to fluctuate during this process, potentially influencing the best course of action. Social media has become a prevalent way for the public to express emotions and opinions in recent times. So that, the sentiment analysis on top of it may detect and provide valuable evidence of public attitude and help governments subsequent formulation of measures and policies. We present Senti-COVID19, an interactive visual analytic system for reflecting and analyzing public sentiment and detecting sentiment fluctuation triggers on social media. Senti-COVID19 adopts lexicon-based sentiment analysis to divulge the public opinion to COVID-19 events, employing libraries to extract keywords and statistics for providing detailed information. In addition, it offers visualizations for presenting the analysis, allowing users to quickly discover relevant information. Our results show that Senti-COVID19 can be used effectively to analyze sentiment from social media text, allowing users to explore derived data and identify insights from the collected tweets.
Highlights
Due to the serious COVID-19 epidemic situation, people’s lives, and emotional states have been affected
We propose Senti-COVID19 (Fig. 1), an interactive visual analytics system for
SentiCOVID19 computes the daily statistics of the sentiment scores, daily tweets count in sentiment categories, and daily keywords to detect the trigger of sentiment fluctuation and identify the sentiment distribution
Summary
Due to the serious COVID-19 epidemic situation, people’s lives, and emotional states have been affected. Most people have had to work and study remotely from home to avoid contact and transmission of the virus This circumstance and the problematic situation of the epidemic may trigger negative emotions, which public policies or political events can amplify. Some studies use health behavior theories and machine learning models to explore the insights and behavior of the public toward COVID-19 [6] Despite their relevance, most studies do not provide an interactive visual analysis for users to discover the public’s dominant sentiment trend or reveal insights [3], [7]. Most studies do not provide an interactive visual analysis for users to discover the public’s dominant sentiment trend or reveal insights [3], [7] To address these issues, we propose Senti-COVID19 (Fig. 1), an interactive visual analytics system for.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
