Abstract: In a rapidly globalizing world, disasters and the way in which they are managed are changing. Social media, in conjunction with other online resources, now provide a wealth of information throughout the lifecycle of disasters and are relied upon by individuals and emergency responders alike. The study of such data as a lens for analysis has proved valuable in recent years, with many contributing to targeted emergency response protocols and improved methods for the management strategies of future crises. This study seeks to make a similar contribution by reporting on the use of such data for situational awareness during the case of hurricane Irma, which occurred between September and August 2017. Using a mixed methods approach the paper examines data from social media such as Twitter, as well as other online sources such as blogs and news media, to provide original insight into the disaster. A conceptual framework is then applied to determine the uses and users of social media, and to identify how these change throughout the course of the disaster, thus demonstrating situational awareness over time. The paper concludes with proposed improvements for disaster management and emergency response for future similar disasters, specifically in the hurricane season, in addition to more generalized hazards which are predicted to increase in their frequency and severity due to underlying issues such as climate change.

Abstract: Conceptual frameworks which seek to integrate social media uses into disaster management strategies are employed in a range of events. With continued variations to social media practices, developments in technology, and changes in online behaviors, it is imperative to provide conceptual frameworks which are relevant, current and insightful. This paper conceptualizes a range of recent literature through an inductive methodology, and presents the themes of Web accessibility and online information reliability as broad and emerging considerations for the identification of social media uses during disasters. It presents a new conceptual framework of current social media uses which may be used to supplement existing frameworks. The framework has been applied to a dataset of Tweets from the 2015 Nepal earthquake to demonstrate its validity. Suggestions for future applications are discussed.

Abstract: This paper considers the role of social media in the response to the flooding of 2011 in Genoa (Italy), caused by flash floods during torrential rainfall. Volunteer students created a Facebook page to communicate with citizens and organize support and rescue activities. In this paper, we first look at the story of the 2011 Genoa floods from the point of view of the news media to gain insights into the imaginaries behind the use of social media in situations of natural disaster. Second, we look at a communication partnership between citizenry and public authorities for its value in building resilience to disaster among communities. Ethical and social dimensions of these partnerships are analysed.

Abstract: In 2004, Information Systems for Crisis Response and Management (ISCRAM) was a new area of research. Pioneering researchers from different continents and disciplines found fellowship at the first ISCRAM work-shop. Around the same time, the use of social media in crises was first recognized in academia. In 2018, the 15th ISCRAM conference will take place, which gives us the possibility to look back on what has already been achieved with regard to IT support in crises using social media. With this article, we examine trends and devel-opments with a specific focus on social media. We analyzed all papers published at previous ISCRAMs (n=1339). Our analysis shows that various platforms, the use of language and coverage of different types of disasters follow certain trends – most noticeably a dominance of Twitter, English and crises with large impacts such as hurricanes or earthquakes can be seen.

Abstract: Recent studies have called attention to the improvement of “collaborative resilience” by fostering the collaboration potentials of public and private stakeholders during disasters. With our research we consider real and virtual volunteers in order to detect conditions for cooperation among those citizen groups through social media. Therefore we analysed the usage of Twitter during a tornado crisis to look for role patterns and aspects that helped volunteer groups in the virtual to emerge, and matched the data with an interview study on experiences, attitudes, concerns and potentials professional emergency services recounted in the emergence of volunteer groups in the real. While virtual groups seem to easily form and collaborate, the engagement of real volunteers is decreasing according to the perception of professionals. We discuss the dynamics in both tendencies and suggest design implications (use of existing social networks, promotion and awareness, connection among volunteers, connection to emergency services and systems) to support both types of volunteer groups, which lead to a software prototype.

Abstract: User-generated content (UGC) on social media can act as a key source of information for emergency responders incrisis situations. However, due to the volume concerned, computational techniques are needed to effectively filter and prioritise this content as it arises during emerging events. In the literature, these techniques are trained using annotated content from previous crises. In this paper, we investigate how this prior knowledge can be best leveraged for new crises by examining the extent to which crisis events of a similar type are more suitable for adaptation tonew events (cross-domain adaptation). Given the recent successes of transformers in various language processing tasks, we propose CAST: an approach for Crisis domain Adaptation leveraging Sequence-to-sequence Transformers. We evaluate CAST using two major crisis-related message classification datasets. Our experiments show that ourCAST-based best run without using any target data achieves the state of the art performance in both in-domain and cross-domain contexts. Moreover, CAST is particularly effective in one-to-one cross-domain adaptation when trained with a larger language model. In many-to-one adaptation where multiple crises are jointly used as the source domain, CAST further improves its performance. In addition, we find that more similar events are more likely to bring better adaptation performance whereas fine-tuning using dissimilar events does not help for adaptation. To aid reproducibility, we open source our code to the community.

Abstract: Recent years have shown that mobile devices and Twitter can play a significant role in providing real-time data from disaster-affected areas to disaster managers. Against this background we present a workflow for Twitter integration into a disaster management information system, and a concept for content moderation that can increase the quality of disseminated information.

Abstract: The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

Abstract: Social media enable rapid, peer-to-peer information flow during crisis events, affordances that have both positive and negative consequences. The potential for spreading misinformation is a significant concern. Drawing on an empirical study of information-sharing practices in a crisis-affected community in the Catskill Mountains after Hurricane Irene, this paper describes how an ad hoc group of community members, led by a handful of journalists, employed specific work practices to mitigate misinformation. We illustrate how the group appropriated specific tools and performed visible skepticism, among other techniques, to help control the spread of false rumors. These findings suggest implications for the design of tools and the development of best practices for supporting community-led, crowd-powered response efforts during disasters.

Abstract: With the advancement and proliferation of technology, non-profit organisations have embraced social media platforms to improve their operational capabilities through brand advocacy, among many other strategies. The effect of such social media campaigns on these institutions, however, remains largely underexplored, especially during disaster periods. This work introduces and applies a quantitative investigative framework to understand how social media influence the behaviour of donors and their usage of these platforms throughout (natural) disasters. More specifically, we explore how on-line engagement – as captured by Facebook interactions and Google search trends – corresponds to the donors’ behaviour during the catastrophic 2019–2020 Australian bushfire season. To discover this relationship, we analyse the record of donations made to the Australian Red Cross throughout this period. Our exploratory study reveals that social media campaigns are effective in encouraging on-line donations made via a dedicated website. We also compare this mode of giving to more regular, direct deposit gifting.

Abstract: Social media are now widely used by affected members of the public during an emergency. As these platforms have become mainstream, governments have responded to the public?s expectation that information is available online, particularly during disasters. Emergency management organizations (EMOs) now widely use social media to communicate with the public alongside occasional intelligence gathering. While EMOs increasingly use social media, breakdowns in internal communication can inhibit the dissemination of timely information to their online followers. Drawing on a two-year ethnography at the Queensland Fire and Emergency Services (QFES), an Australian EMO, this paper outlines how the organization uses social media to disseminate information during emergencies and identifies the internal tensions around its use. These tensions include the prioritization of operational duties over public information responsibilities, and the difficulties around requesting and receiving information from operational personnel located on the ground.

Abstract: Event detection from social media is a challenging task due to the volume, the velocity and the variety of user-generated data requiring real-time processing. Despite recent works on this subject, a generalized and scalable approach that could be applied across languages and topics has not been consolidated, yet. In this paper, we propose a methodology for real-time event detection from Twitter data that allows users to select a topic of interest by defining a simple set of keywords and a matching rule. We implement the proposed methodology and evaluate it with real data to detect different types of events.