During the COVID-19 pandemic, information is being rapidly shared by public health experts and researchers through social media platforms. Whilst government policies were disseminated and discussed, fake news and misinformation simultaneously created a corresponding wave of “infodemics.” This study analyzed the discourse on Twitter in several languages, investigating the reactions to government and public health agency social media accounts that share policy decisions and official messages. The study collected messages from 21 official Twitter accounts of governments and public health authorities in the UK, US, Mexico, Canada, Brazil, Spain, and Nigeria, from 15 March to 29 May 2020. Over 2 million tweets in various languages were analyzed using a mixed-methods approach to understand the messages both quantitatively and qualitatively. Using automatic, text-based clustering, five topics were identified for each account and then categorized into 10 emerging themes. Identified themes include political, socio-economic, and population-protection issues, encompassing global, national, and individual levels. A comparison was performed amongst the seven countries analyzed and the United Kingdom (Scotland, Northern Ireland, and England) to find similarities and differences between countries and government agencies. Despite the difference in language, country of origin, epidemiological contexts within the countries, significant similarities emerged. Our results suggest that other than general announcement and reportage messages, the most-discussed topic is evidence-based leadership and policymaking, followed by how to manage socio-economic consequences.

No abstract

No abstract

Relevant and timely information collected from social media during crises can be an invaluable resource for emergency management. However, extracting this information remains a challenging task, particularly when dealing with social media postings in multiple languages. This work proposes a cross-lingual method for retrieving and summarizing crisis-relevant information from social media postings. We describe a uniform way of expressing various information needs through structured queries and a way of creating summaries answering those information needs. The method is based on multilingual transformers embeddings. Queries are written in one of the languages supported by the embeddings, and the extracted sentences can be in any of the other languages supported. Abstractive summaries are created by transformers. The evaluation, done by crowdsourcing evaluators and emergency management experts, and carried out on collections extracted from Twitter during five large-scale disasters spanning ten languages, shows the flexibility of our approach. The generated summaries are regarded as more focused, structured, and coherent than existing state-of-the-art methods, and experts compare them favorably against summaries created by existing, state-of-the-art methods.

No abstract