Social media use in disaster recovery: A systematic literature review

A comprehensive review of online, official, and scientific literature was carried out in 2012-13 to develop a framework of disaster social media. This framework can be used to facilitate the creation of disaster social media tools, the formulation of disaster social media implementation processes, and the scientific study of disaster social media effects. Disaster social media users in the framework include communities, government, individuals, organisations, and media outlets. Fifteen distinct disaster social media uses were identified, ranging from preparing and receiving disaster preparedness information and warnings and signalling and detecting disasters prior to an event to (re)connecting community members following a disaster. The framework illustrates that a variety of entities may utilise and produce disaster social media content. Consequently, disaster social media use can be conceptualised as occurring at a number of levels, even within the same disaster. Suggestions are provided on how the proposed framework can inform future disaster social media development and research.

This paper reviews the actual and potential use of social media in emergency, disaster and crisis situations. This is a field that has generated intense interest. It is characterised by a burgeoning but small and very recent literature. In the emergencies field, social media (blogs, messaging, sites such as Facebook, wikis and so on) are used in seven different ways: listening to public debate, monitoring situations, extending emergency response and management, crowd-sourcing and collaborative development, creating social cohesion, furthering causes (including charitable donation) and enhancing research. Appreciation of the positive side of social media is balanced by their potential for negative developments, such as disseminating rumours, undermining authority and promoting terrorist acts. This leads to an examination of the ethics of social media usage in crisis situations. Despite some clearly identifiable risks, for example regarding the violation of privacy, it appears that public consensus on ethics will tend to override unscrupulous attempts to subvert the media. Moreover, social media are a robust means of exposing corruption and malpractice. In synthesis, the widespread adoption and use of social media by members of the public throughout the world heralds a new age in which it is imperative that emergency managers adapt their working practices to the challenge and potential of this development. At the same time, they must heed the ethical warnings and ensure that social media are not abused or misused when crises and emergencies occur.

Background The coronavirus disease (COVID-19) pandemic is a global health emergency with over 6 million cases worldwide as of the beginning of June 2020. The pandemic is historic in scope and precedent given its emergence in an increasingly digital era. Importantly, there have been concerns about the accuracy of COVID-19 case counts due to issues such as lack of access to testing and difficulty in measuring recoveries. Objective The aims of this study were to detect and characterize user-generated conversations that could be associated with COVID-19-related symptoms, experiences with access to testing, and mentions of disease recovery using an unsupervised machine learning approach. Methods Tweets were collected from the Twitter public streaming application programming interface from March 3-20, 2020, filtered for general COVID-19-related keywords and then further filtered for terms that could be related to COVID-19 symptoms as self-reported by users. Tweets were analyzed using an unsupervised machine learning approach called the biterm topic model (BTM), where groups of tweets containing the same word-related themes were separated into topic clusters that included conversations about symptoms, testing, and recovery. Tweets in these clusters were then extracted and manually annotated for content analysis and assessed for their statistical and geographic characteristics. Results A total of 4,492,954 tweets were collected that contained terms that could be related to COVID-19 symptoms. After using BTM to identify relevant topic clusters and removing duplicate tweets, we identified a total of 3465 (<1%) tweets that included user-generated conversations about experiences that users associated with possible COVID-19 symptoms and other disease experiences. These tweets were grouped into five main categories including first- and secondhand reports of symptoms, symptom reporting concurrent with lack of testing, discussion of recovery, confirmation of negative COVID-19 diagnosis after receiving testing, and users recalling symptoms and questioning whether they might have been previously infected with COVID-19. The co-occurrence of tweets for these themes was statistically significant for users reporting symptoms with a lack of testing and with a discussion of recovery. A total of 63% (n=1112) of the geotagged tweets were located in the United States. Conclusions This study used unsupervised machine learning for the purposes of characterizing self-reporting of symptoms, experiences with testing, and mentions of recovery related to COVID-19. Many users reported symptoms they thought were related to COVID-19, but they were not able to get tested to confirm their concerns. In the absence of testing availability and confirmation, accurate case estimations for this period of the outbreak may never be known. Future studies should continue to explore the utility of infoveillance approaches to estimate COVID-19 disease severity.