tetano
Editor, Senior Moderator
Clin Infect Dis
. 2022 May 15;74(Supplement_3):e4-e9.
doi: 10.1093/cid/ciac141.
Exploring Coronavirus Disease 2019 Vaccine Hesitancy on Twitter Using Sentiment Analysis and Natural Language Processing Algorithms
Anasse Bari[SUP] 1 [/SUP], Matthias Heymann[SUP] 1 [/SUP], Ryan J Cohen[SUP] 1 [/SUP], Robin Zhao[SUP] 1 [/SUP], Levente Szabo[SUP] 1 [/SUP], Shailesh Apas Vasandani[SUP] 1 [/SUP], Aashish Khubchandani[SUP] 1 [/SUP], Madeline DiLorenzo[SUP] 2 [/SUP], Megan Coffee[SUP] 2 [/SUP]
Affiliations
Abstract
Background: Vaccination can help control the coronavirus disease 2019 (COVID-19) pandemic but is undermined by vaccine hesitancy. Social media disseminates information and misinformation regarding vaccination. Tracking and analyzing social media vaccine sentiment could better prepare health professionals for vaccination conversations and campaigns.
Methods: A real-time big data analytics framework was developed using natural language processing sentiment analysis, a form of artificial intelligence. The framework ingests, processes, and analyzes tweets for sentiment and content themes, such as natural health or personal freedom, in real time. A later dataset evaluated the relationship between Twitter sentiment scores and vaccination rates in the United States.
Results: The real-time analytics framework showed a widening gap in sentiment with more negative sentiment after vaccine rollout. After rollout, using a static dataset, an increase in positive sentiment was followed by an increase in vaccination. Lag cross-correlation analysis across US regions showed evidence that once all adults were eligible for vaccination, the sentiment score consistently correlated with vaccination rate with a lag of around 1 week. The Granger causality test further demonstrated that tweet sentiment scores may help predict vaccination rates.
Conclusions: Social media has influenced the COVID-19 response through valuable information and misinformation and distrust. This tool was used to collect and analyze tweets at scale in real time to study sentiment and key terms of interest. Separate tweet analysis showed that vaccination rates tracked regionally with Twitter vaccine sentiment and might forecast changes in vaccine uptake and/or guide targeted social media and vaccination strategies. Further work is needed to analyze the interplay between specific populations, vaccine sentiment, and vaccination rates.
Keywords: COVID-19; Twitter; artificial intelligence; vaccination; vaccine hesitancy.
. 2022 May 15;74(Supplement_3):e4-e9.
doi: 10.1093/cid/ciac141.
Exploring Coronavirus Disease 2019 Vaccine Hesitancy on Twitter Using Sentiment Analysis and Natural Language Processing Algorithms
Anasse Bari[SUP] 1 [/SUP], Matthias Heymann[SUP] 1 [/SUP], Ryan J Cohen[SUP] 1 [/SUP], Robin Zhao[SUP] 1 [/SUP], Levente Szabo[SUP] 1 [/SUP], Shailesh Apas Vasandani[SUP] 1 [/SUP], Aashish Khubchandani[SUP] 1 [/SUP], Madeline DiLorenzo[SUP] 2 [/SUP], Megan Coffee[SUP] 2 [/SUP]
Affiliations
- PMID: 35568473
- DOI: 10.1093/cid/ciac141
Abstract
Background: Vaccination can help control the coronavirus disease 2019 (COVID-19) pandemic but is undermined by vaccine hesitancy. Social media disseminates information and misinformation regarding vaccination. Tracking and analyzing social media vaccine sentiment could better prepare health professionals for vaccination conversations and campaigns.
Methods: A real-time big data analytics framework was developed using natural language processing sentiment analysis, a form of artificial intelligence. The framework ingests, processes, and analyzes tweets for sentiment and content themes, such as natural health or personal freedom, in real time. A later dataset evaluated the relationship between Twitter sentiment scores and vaccination rates in the United States.
Results: The real-time analytics framework showed a widening gap in sentiment with more negative sentiment after vaccine rollout. After rollout, using a static dataset, an increase in positive sentiment was followed by an increase in vaccination. Lag cross-correlation analysis across US regions showed evidence that once all adults were eligible for vaccination, the sentiment score consistently correlated with vaccination rate with a lag of around 1 week. The Granger causality test further demonstrated that tweet sentiment scores may help predict vaccination rates.
Conclusions: Social media has influenced the COVID-19 response through valuable information and misinformation and distrust. This tool was used to collect and analyze tweets at scale in real time to study sentiment and key terms of interest. Separate tweet analysis showed that vaccination rates tracked regionally with Twitter vaccine sentiment and might forecast changes in vaccine uptake and/or guide targeted social media and vaccination strategies. Further work is needed to analyze the interplay between specific populations, vaccine sentiment, and vaccination rates.
Keywords: COVID-19; Twitter; artificial intelligence; vaccination; vaccine hesitancy.