2021/03/29 by Massimo Stella, Michael S. Vitevitch, Stella, Massimo +3 · 2 citations
Computer Science · Medicine · Neuroscience · Physics and Astronomy · Psychology · Social Sciences · #Anger #Computation and Language (cs.CL) #Computer science #Computers and Society (cs.CY) #Disgust #FOS: Computer and information sciences #FOS: Physical sciences #Framing (construction) #History #Misinformation and Its Impacts #Persuasion #Physics and Society (physics.soc-ph) #Psychology #Psychology of Moral and Emotional Judgment #SARS-CoV-2 and COVID-19 Research #Sadness #Sentiment analysis #Social and Information Networks (cs.SI) #Social media #Social psychology #Vaccine Coverage and Hesitancy #World Wide Web #cs.CL #cs.CY #cs.SI #physics.soc-ph
paper · pdf · doi:10.48550/arxiv.2103.15909
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/03/29 · openalex publication_date 2021/03/29 · arxiv updated 2021/03/31 · openalex created_date 2022/07/25 · openalex updated_date 2026/08/08
Monitoring social discourse about COVID-19 vaccines is key to understanding\nhow large populations perceive vaccination campaigns. We focus on 4765 unique\npopular tweets in English or Italian about COVID-19 vaccines between 12/2020\nand 03/2021. One popular English tweet was liked up to 495,000 times, stressing\nhow popular tweets affected cognitively massive populations. We investigate\nboth text and multimedia in tweets, building a knowledge graph of\nsyntactic/semantic associations in messages including visual features and\nindicating how online users framed social discourse mostly around the logistics\nof vaccine distribution. The English semantic frame of "vaccine" was highly\npolarised between trust/anticipation (towards the vaccine as a scientific asset\nsaving lives) and anger/sadness (mentioning critical issues with dose\nadministering). Semantic associations with "vaccine," "hoax" and conspiratorial\njargon indicated the persistence of conspiracy theories and vaccines in\nmassively read English posts (absent in Italian messages). The image analysis\nfound that popular tweets with images of people wearing face masks used\nlanguage lacking the trust and joy found in tweets showing people with no\nmasks, indicating a negative affect attributed to face covering in social\ndiscourse. A behavioural analysis revealed a tendency for users to share\ncontent eliciting joy, sadness and disgust and to like less sad messages,\nhighlighting an interplay between emotions and content diffusion beyond\nsentiment. With the AstraZeneca vaccine being suspended in mid March 2021,\n"Astrazeneca" was associated with trustful language driven by experts, but\npopular Italian tweets framed "vaccine" by crucially replacing earlier levels\nof trust with deep sadness. Our results stress how cognitive networks and\ninnovative multimedia processing open new ways for reconstructing online\nperceptions about vaccines and trust.\n