Global spatiotemporal trends and determinants of COVID-19 vaccine acceptance on Twitter: a multilingual deep learning study in 135 countries and territories

BackgroundCOVID-19 vaccination has faced a range of challenges from supply-side barriers such as insufficient vaccine supply and negative information environment and demand-side barriers centring on public acceptance and confidence in vaccines. This study assessed global spatiotemporal trends in demand- and supply-side barriers to vaccine uptake using COVID-19-related social media data and explored the country-level determinants of vaccine acceptance. MethodsWe accessed a total of 13,093,406 tweets sent between November 2020 and March 2022 about the COVID-19 vaccine in 90 languages from 135 countries using Meltwater(R) (a social listening platform). Based on 8,125 manually-annotated tweets, we fine-tuned multilingual deep learning models to automatically annotate all 13,093,406 tweets. We present spatial and temporal trends in four key spheres: (1) COVID-19 vaccine acceptance; (2) confidence in COVID-19 vaccines; (3) the online information environment regarding the COVID-19 vaccine; and (4) perceived supply-side barriers to COVID-19 vaccination. Using univariate and multilevel regressions, we evaluated the association between COVID-19 vaccine acceptance on Twitter(R) and (1) country-level characteristics regarding governance, pandemic preparedness, trust, culture, social development, and population demographics; (2) country-level COVID-19 vaccine coverage; and (3) Google(R) search trends on adverse vaccine events. FindingsCOVID-19 vaccine acceptance was high among Twitter(R) users in Southeast Asian, Eastern Mediterranean, and Western Pacific countries, including India, Indonesia, and Pakistan. In contrast, acceptance was relatively low in high-income nations like South Korea, Japan, and the Netherlands. Spatial variations were correlated with country-level governance, pandemic preparedness, public trust, culture, social development, and demographic determinants. At the country level, vaccine acceptance sentiments expressed on Twitter(R) predicted higher vaccine coverage. We noted the declining trend of COVID-19 vaccine acceptance among global Twitter(R) users since March 2021, which was associated with increased searches for adverse vaccine events. Interpretation In future pandemics, new vaccines may face the potential low-level and declining trend in acceptance, like COVID-19 vaccines, and early responses are needed. Social media mining represents a promising surveillance approach to monitor vaccine acceptance and can be validated against real-world vaccine uptake data. FundingNational Natural Science Foundation of China.

Monitoring global trends in Covid-19 vaccination intention and confidence: a social media-based deep learning study

BackgroundThis study developed deep learning models to monitor global intention and confidence of Covid-19 vaccination in real time. MethodsWe collected 6.73 million English tweets regarding Covid-19 vaccination globally from January 2020 to February 2021. Fine-tuned Transformer-based deep learning models were used to classify tweets in real time as they relate to Covid-19 vaccination intention and confidence. Temporal and spatial trends were performed to map the global prevalence of Covid-19 vaccination intention and confidence, and public engagement on social media was analyzed. FindingsGlobally, the proportion of tweets indicating intent to accept Covid-19 vaccination declined from 64.49% on March to 39.54% on September 2020, and then began to recover, reaching 52.56% in early 2021. This recovery in vaccine acceptance was largely driven by the US and European region, whereas other regions experienced the declining trends in 2020. Intent to accept and confidence of Covid-19 vaccination were relatively high in South-East Asia, Eastern Mediterranean, and Western Pacific regions, but low in American, European, and African regions. 12.71% tweets expressed misinformation or rumors in South Korea, 14.04% expressed distrust in government in the US, and 16.16% expressed Covid-19 vaccine being unsafe in Greece, ranking first globally. Negative tweets, especially misinformation or rumors, were more engaged by twitters with fewer followers than positive tweets. InterpretationThis global real-time surveillance study highlights the importance of deep learning based social media monitoring to detect emerging trends of Covid-19 vaccination intention and confidence to inform timely interventions. FundingNational Natural Science Foundation of China. Research in contextO_ST_ABSEvidence before this studyC_ST_ABSWith COVID-19 vaccine rollout, each country should investigate its vaccination intention in local contexts to ensure massive vaccination. We searched PubMed for all articles/preprints until April 9, 2021 with the keywords "("Covid-19 vaccines"[Mesh] OR Covid-19 vaccin*[TI]) AND (confidence[TI] OR hesitancy[TI] OR acceptance[TI] OR intention[TI])". We identified more than 100 studies, most of which are country-level cross-sectional surveys, and the largest global survey of Covid-19 vaccine acceptance only covered 32 countries to date. However, how Covid-19 vaccination intention changes over time remain unknown, and many countries are not covered in previous surveys yet. A few studies assessed public sentiments towards Covid-19 vaccination using social media data, but only targeting limited geographical areas. There is a lack of real-time surveillance, and no study to date has globally monitored Covid-19 vaccination intention in real time. Added value of this studyTo our knowledge, this is the largest global monitoring study of Covid-19 vaccination intention and confidence with social media data in over 100 countries from the beginning of the pandemic to February 2021. This study developed deep learning models by fine-tuning a Bidirectional Encoder Representation from Transformer (BERT)-based model with 8000 manually-classified tweets, which can be used to monitor Covid-19 vaccination beliefs using social media data in real time. It achieves temporal and spatial analyses of the evolving beliefs to Covid-19 vaccines across the world, and also an insight for many countries not yet covered in previous surveys. This study highlights that the intention to accept Covid-19 vaccination have experienced a declining trend since the beginning of the pandemic in all world regions, with some regions recovering recently, though not to their original levels. This recovery was largely driven by the US and European region (EUR), whereas other regions experienced the declining trends in 2020. Intention to accept and confidence of Covid-19 vaccination were relatively high in South-East Asia region (SEAR), Eastern Mediterranean region (EMR), and Western Pacific region (WPR), but low in American region (AMR), EUR, and African region (AFR). Many AFR countries worried more about vaccine effectiveness, while EUR, AMR, and WPR concerned more about vaccine safety (the most concerns with 16.16% in Greece). Online misinformation or rumors were widespread in AMR, EUR, and South Korea (12.71%, ranks first globally), and distrust in government was more prevalent in AMR (14.04% in the US, ranks first globally). Our findings can be used as a reference point for survey data on a single country in the future, and inform timely and specific interventions for each country to address Covid-19 vaccine hesitancy. Implications of all the available evidenceThis global real-time surveillance study highlights the importance of deep learning based social media monitoring as a quick and effective method for detecting emerging trends of Covid-19 vaccination intention and confidence to inform timely interventions, especially in settings with limited sources and urgent timelines. Future research should build multilingual deep learning models and monitor Covid-19 vaccination intention and confidence in real time with data from multiple social media platforms.

Assessment of public attention, risk perception, emotional and behavioural responses to the COVID-19 outbreak: social media surveillance in China

BackgroundUsing social media surveillance data, this study aimed to assess public attention, risk perception, emotion, and behavioural response to the COVID-19 outbreak in real time. MethodsWe collected data from most popular social medias: Sina Weibo, Baidu search engine, and Ali e-commerce marketplace, from 1 Dec 2019 to 15 Feb 2020. Weibo post counts and Baidu searches were used to generate indices assessing public attention. Public intention and actual adoption of recommended protection measures or panic buying triggered by rumours and misinformation were measured by Baidu and Ali indices. Qualitative Weibo posts were analysed by the Linguistic Inquiry and Word Count text analysis programme to assess public emotion responses to epidemiological events, governments announcements, and control measures. FindingsWe identified two missed windows of opportunity for early epidemic control of the COVID-19 outbreak, one in Dec 2019 and the other between 31 Dec and 19 Jan, when public attention was very low despite the emerging outbreak. Delayed release of information ignited negative public emotions. The public responded quickly to government announcements and adopted recommended behaviours according to issued guidelines. We found rumours and misinformation regarding remedies and cures led to panic buying during the outbreak, and timely clarification of rumours effectively reduced irrational behaviour. InterpretationSocial media surveillance can enable timely assessments of public reaction to risk communication and epidemic control measures, and the immediate clarification of rumours. This should be fully incorporated into epidemic preparedness and response systems. FundingNational Natural Science Foundation of China.

Public Exposure to Live Animals, Behavioural Change, and Support in Containment Measures in response to COVID-19 Outbreak: a population-based cross sectional survey in China

BackgroundIn response to the COVID-19 outbreak, we aimed to investigate behavioural change on exposure to live animals before and during the outbreak, and public support and confidence for governmental containment measures. MethodsA population-based cross-sectional telephone survey via random dialing was conducted in Wuhan (the epicentre) and Shanghai (an affected city with imported cases) between 1 and 10 February, 2020. 510 residents in Wuhan and 501 residents in Shanghai were randomly sampled. Differences of outcome measures were compared before and during the outbreak, and between two cities. FindingsProportion of respondents visiting wet markets at usual was 23.3% (119/510) in Wuhan and 20.4% (102/501) in Shanghai. During the outbreak, it decreased to 3.1% (16) in Wuhan (p<0{middle dot}001), and 4.4% (22) in Shanghai (p<0{middle dot}001). Proportion of those consuming wild animal products declined from 10.2% (52) to 0.6% (3) in Wuhan (p<0{middle dot}001), and from 5.2% (26) to 0.8% (4) in Shanghai (p<0{middle dot}001). 79.0% (403) of respondents in Wuhan and 66.9% (335) of respondents in Shanghai supported permanent closure of wet markets (P<0.001). 95% and 92% of respondents supported banning wild animal trade and quarantining Wuhan, and 75% were confident towards containment measures. Females and the more educated were more supportive for the above containment measures. InterpretationThe public responded quickly to the outbreak, and reduced exposure to live animals, especially in Wuhan. With high public support in containment measures, better regulation of wet markets and healthy diets should be promoted. FundingNational Science Fund for Distinguished Young Scholars, H2020 MOOD project. Research in contextO_ST_ABSEvidence before this studyC_ST_ABSOn February 19, 2020, we searched PubMed for papers published after January 1, 2020, containing the following terms: "2019 nCoV" or "COVID-19". We identified 179 studies, most of which are research on clinical and epidemiological characteristics of COVID-19. To date there is no primary research to quantify public behavioural response and support in containment measures in response to the outbreak. Only four commentaries mentioned the influence of the outbreak on mental health. One commentary introduced the habit of consuming wild animal products in China. Another commentary briefly introduced isolation, quarantine, social distancing and community containment as public health measures in the outbreak. The Chinese government has introduced a series of strict containment measures, and societal acceptability of these measure is important for effective and sustained response. Evidence is urgently needed to help policy makers understand public response to the outbreak and support for the containment measures, but no evidence available to date. Added value of this studyWe conducted a population-based cross-sectional telephone survey via random digital dialing in Wuhan (the epicentre) and Shanghai (an affected city with imported cases) between 1 and 10 February, 2020. To date, this is the only few analyses on behavioural response to the outbreak and societal acceptability of governmental containment measures, which has been listed as the current priority of China CDC. We provide an assessment of behavioural change on exposure to live animals during the outbreak, by comparison before and during the outbreak, and between two cities with diverse exposure intensities to COVID-19. We also provide evidence on public support in governmental containment measures, including strict regulation on wet markets to reduce animal-to-human transmission and city quarantine to reduce human transmission. Implications of all the available evidenceWe found that wild animal consumption was more prevalent in Wuhan (10.2%) than in Shanghai (5.2%). The public responded quickly to the outbreak, and significantly reduced exposure to live animals and stopped wild animal consumption, especially in Wuhan. They were very supportive of governmental containment measures. With high public support, wet markets should be better regulated, and healthy diets, including changing the traditional habit of eating wild animal products, should be promoted. This can inform policy makers in China and other countries to implement and adjust containment strategies in response to the outbreak in the future.

The Effect of Vaccine Literacy on Parental Trust and Intention to Vaccinate after a Major Vaccine Scandal.

Health literacy, and more specifically vaccine literacy, might be an important factor in reducing the negative effects of exposure to misleading reports on vaccination. This study explores the association between vaccine literacy and vaccination-related outcomes after misleading reports on a scandal concerning locally produced childhood vaccines had emerged in 2016 in China. Data for this study came from a cross-sectional survey, which was conducted in April 2016 in Hangzhou, China. Data were collected in kindergartens and community health centers among parents of children up to 6 years of age. Data were analyzed for 1864 participants. Binary logistic regression models showed that, after controlling for socio-demographics and children's age, parents who had better vaccine literacy (<0.05) were more likely to trust and choose domestically produced vaccines, which account for about 95% of the total vaccinations in China. This study provides evidence on a still largely understudied relationship between vaccine literacy and vaccination-related outcomes. Findings might suggest that higher literacy levels could reduce some of the negative effects of being exposed to misleading information on vaccination, eventually leading to less vaccination hesitancy.