Exploring Coronavirus Disease 2019 Vaccine Hesitancy on Twitter Using Sentiment Analysis and Natural Language Processing Algorithms.

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.

COVID-19 early-alert signals using human behavior alternative data.

Google searches create a window into population-wide thoughts and plans not just of individuals, but populations at large. Since the outbreak of COVID-19 and the non-pharmaceutical interventions introduced to contain it, searches for socially distanced activities have trended. We hypothesize that trends in the volume of search queries related to activities associated with COVID-19 transmission correlate with subsequent COVID-19 caseloads. We present a preliminary analytics framework that examines the relationship between Google search queries and the number of newly confirmed COVID-19 cases in the United States. We designed an experimental tool with search volume indices to track interest in queries related to two themes: isolation and mobility. Our goal was to capture the underlying social dynamics of an unprecedented pandemic using alternative data sources that are new to epidemiology. Our results indicate that the net movement index we defined correlates with COVID-19 weekly new case growth rate with a lag of between 10 and 14 days for the United States at-large, as well as at the state level for 42 out of 50 states with the exception of 8 states (DE, IA, KS, NE, ND, SD, WV, WY) from March to June 2020. In addition, an increasing caseload was seen over the summer in some southern US states. A sharp rise in mobility indices was followed by a sharp increase, respectively, in the case growth data, as seen in our case study of Arizona, California, Florida, and Texas. A sharp decline in mobility indices is often followed by a sharp decline, respectively, in the case growth data, as seen in our case study of Arizona, California, Florida, Texas, and New York. The digital epidemiology framework presented here aims to discover predictors of the pandemic's curve, which could supplement traditional predictive models and inform early warning systems and public health policies.