Abstract: Despite the outpouring of social support posted to social media channels in the aftermath of disaster, finding and managing content that can translate into community relief, donations, volunteering, or other recovery support is difficult due to the lack of sufficient annotated data around volunteerism. This paper outlines three experiments to alleviate these difficulties. First, we estimate to what degree volunteerism content from one crisis is transferable to another by evaluating the consistency of language in volunteer-and donation-related social media content across 78 disasters. Second it introduces methods for providing computational support in this emergency support function and developing semi-automated models for classifying volunteer-and donation-related social media content in new disaster events. Results show volunteer-and donation-related social media content is sufficiently similar across disasters and disaster types to warrant transferring models across disasters, and we evaluate simple resampling techniques for tuning these models. We then introduce and evaluate a weak-supervision approach to integrate domain knowledge from emergency response officers with machine learningmodelstoimproveclassification accuracy andacceleratethisemergencysupportinnewevents. This method helps to overcome the scarcity in data that we observe related to volunteer-and donation-related social media content.

Abstract: Radiation measurements are key information in post-nuclear accident situations. Automated Twitter accounts have been used to share the readings, but often in an incomplete way from the perspective of data sharing and risk communication between citizen and radiation experts. In this paper, we investigate the requirements for radiation measurements completeness, by analyzing the perceived usefulness of several metadata items that may go along the measurement itself. We carried out a benchmark of existing uses, and conducted a survey with both experts and lay citizens. We thus produced a set of guidelines regarding the metadata that should be used, and the way to publish it.

Abstract: We report on the design, development, and evaluation of a user labeling framework for social media monitoring by emergency responders. By labeling Twitter user accounts based on behavior and content, this novel approach identifies tweets from accounts belonging to Individuals generating Personalized content and captures information that might otherwise be missed. We evaluate the framework using training data from the 2018 Camp, Woolsey, and Hill fires. Approximately 30% of the Individual-Personalized tweets contain first-hand information, providing a rich stream of content for social media monitoring. Because it can quickly eliminate most redundant tweets, this framework could be a critical first step in an end-to-end information extraction pipeline. It may also generalize more easily for new disaster events since it relies on general user account attributes rather than tweet content. We conclude with next steps for refining and evaluating our framework in near real-time during a disaster response.

Abstract: The theme of ISCRAM 2016 is Resilience. Resilience has become a popular topic in emergency response and crisis management. This edition will highlight the exploration of the various facets of resilience when applied to Crisis and Emergency Management. The purpose of ISCRAM 2016 is to stimulate discussions that enable the design of resilient systems in the domain of crisis management.

Abstract: The theme of ISCRAM 2021 is ?Embracing the Interdisciplinary Nature of Crisis Management.? These
proceedings highlight the range of interdisciplinary research required to understand the design, behavior,
and performance of crisis and emergency management systems. We are pleased to present the included
papers, which offer excellent contributions on a wide range of topics related to the use of information
systems in crisis response and management.

Abstract: The proceedings contain 63 papers and 34 PowerPoint presentations. The topics discussed include: a security risk analysis framework for interconnected transportation systems; learning about emergency management information systems through partially distributed team projects; startle points: a proposed framework for identifying situational cues, and developing realistic emergency training scenarios; assessing the economic value of early warning systems; on the effectiveness of mobile service notification for passenger egress during large public events; social software as an infrastructure for crisis management – a case study about current practice and potential usage; an agent-based approach to envision the future; and dialogical emergency management and strategic awareness in emergency communication.

Abstract: We discuss the results of a research project aimed at exploring the use of social media in emergency communication by officers operating at a local level. We performed 16 semi-structured interviews with national level expert informants, and with officers operating at the municipality and province (prefectures) level in an Italian region (respondents were selected based on their involvement in emergency communication and/or emergency management processes). Social media usage appears distributed over a continuum of engagement, ranging from very basic usage to using social media by adopting a broadcasting approach, to deeper engagement, which also includes continuous interaction with citizens. Two main attitudes emerge both in the narrative style and in social media representations: some respondents seem to adopt an institutional attitude, while others adopt a practical-professional attitude. Among the main barriers to a broader adoption of social media, cultural considerations seem to prevail, along with the lack of personnel, a general concern toward social media communication reliability, and the perceived distance between the formal role of institutions and the informal nature of social media communication.

Abstract: We describe the creation of a building inventory database that is created for Wellington, New Zealand's earthquake-prone capital city. This database aims to assist the generation of research on the risks, impacts, and viable solutions for reducing the seismic risk of existing multi-story concrete buildings in Wellington's Central Business District. The database includes structural, economic and market information on every building in the CDB. Its primary purpose is to inform a multi-disciplinary project whose aims are: (1) to provide best scientific knowledge about the expected seismic performance of concrete buildings; (2) to assess the impact of multiple building failures including the downstream consequences of associated cordoning; (3) to provide a path for seismic retrofitting that includes prioritization of retrofits; and (4) to inform the design of a regulatory structure that can facilitate the reduction of risk associated with earthquake vulnerable concrete buildings as described in aims (1)-(3).

Abstract: This paper presents a user configurable monitoring system to track in near-real-time tweets describing fire events. The system targets fire related words in a user defined region of interest published on Twitter which are further processed by a text classifier to determine if they describe a known fire event of interest. The system was motivated from a case study that examined a corpus of tweets posted during active bushfires. This demonstrated that useful information is available on Twitter about fire events from people who are in the vicinity.
We present an overview of the system describing how it is initially configured by a user to focus on specific fire events in Australia, the development of a text classifier to identify tweets of interest, especially those with accompanying photos, and the monitoring system that can track multiple events at once.

Abstract: Identifying a chemical, biological, radiological, and nuclear incident (CBRN) is a challenge. Evidence and health symptoms resulting from CBRN malevolent incident overlap with other normal non malevolent human activities. However, proper fusion of symptoms and evidence can aid in drawing conclusions with a certain degree of credibility about the existence of an incident. There are two types of incidents directly observable, overt, or indirectly observable, covert, which can be detected from the symptoms and consequences. This paper describes a framework for identifying a CBRN incident from available evidence using a fuzzy belief degree distributed approach. We present two approaches for evidence fusion and aggregation; the first, two level cumulative belief degree (CBD) while the second is ordered weighted aggregation of belief degrees (OWA). The evaluation approach undertaken shows the potential value of the two techniques.

Abstract: Content shared in microblogs during disasters is expressed in various formats and languages. This diversity makes the information retrieval process more complex and computationally infeasible in real time. To address this, we propose a classification model for the identification of prominent users who are sharing relevant and exclusive information during the disaster. Users who have shared at least one tweet about the disaster are modeled using three kinds of time-sensitive features, including topical, social and geographical features. Then, these users are classified into two classes using a linear Support Vector Machine (SVM) to evaluate them over the extracted features and identify the most prominent ones. The first results using the actual dataset, show that our model has a high accuracy by detecting most of the prominent users. Moreover, we demonstrate that all the proposed features used by our model are indispensable to achieve this high accuracy.

Abstract: Recently, we are witnessing the progressive increase in the occurrence of large-scale disasters, characterized by an overwhelming scale and number of causalities. After 72 hours from the disaster occurrence, the damaged area is interested by assessment, reconstruction and recovery actions from several heterogeneous organizations, which need to collaborate and being orchestrated by a centralized authority. This situation requires an effective data sharing by means of a proper middleware platform able to let such organizations to interoperate despite of their differences. Although international organizations have defined collaboration frameworks at the higher level, there is no ICT supporting platform at operational level able to realize the data sharing demanded by such collaborative frameworks. This work proposes a layered architecture and a preliminary implementation of such a middleware for messaging, data and knowledge management. We also illustrate a demonstration of the usability of such an implementation, so as to show the achievable interoperability.