Abstract: We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.

Abstract: The purpose of this paper is to outline the requirement for data-driven methods for determining optimal geographic locations of United States Department of Defense (DOD) Humanitarian Assistance (HA) resources, including disaster mitigation and preparedness projects. HA project managers and tactical implementers charged with cost-efficient deployment of HA resources are challenged to produce measurable effects, in addition to contributing to broader Joint and Interagency-informed security assistance strategies. To address these issues, our ongoing research advocates geospatial multi-criteria site suitability decision support capabilities that leverage 1) existing geospatial resource location-allocation methodology as applied in government, retail, and commercial sectors; 2) user-generated criteria and objective preferences applied in widely-used decision frameworks; 3) assessments of the feasibility of obtaining data at a geographic scale where DOD tactical/operational level users can benefit from the model outputs; and 4) social science theory related to the HA domain criteria that form the foundation of potential decision models.

Abstract: Collabbit is an open source web-based application that aims to increase emergency management efficiency through distributed asynchronous information sharing. The software is targeted to loosely coupled non-profit disaster relief agencies that coordinate response to and recovery from disasters. Disaster relief agencies create a common operating picture of an emergency incident through remotely posted incident updates. Individual users subscribe to topics of interest and receive near-instantaneous updates on those topics. Where information is lacking, users may access a topically organized contact registry. This report describes the development and deployment of the Collabbit project.

Abstract: Natural disasters such as hurricanes, floods, earthquakes, fires as well as those of manmade origins, such as dam breaches, necessitate communication between and among emergency responders, governmental officials, and the impacted populace. As the third largest country in terms of area and first in terms of population, China is no stranger to natural and manmade disasters of varying kinds. Until recently, the country had no central focus on dealing with such events and allowed local officials for the most part to plan and carry out all of the activities involved in disaster planning and management. Advances in the Chinese economy and more of a nationalist slant on policies have attempted to broaden the planning scope and management across the country with varying results. The deployment of wireless communications across China has assisted in disaster planning and management activities, but inconsistent policies and a haphazard approach to its deployment have hindered its ability to fully aid such activities. With a population of more than 1.3 billion (2010 Census) and its wide geography, China is one of the most natural disaster-affected countries in the world. Many natural disasters occur in China frequently and often result in severe damage and loss of life. In response to these events, several strategies for emergency management should be implemented, but in particular the integration of the deployment of wireless networks throughout the rural parts of the country with disaster/emergency planning for the same areas should be undertaken. © 2012 ISCRAM.

Abstract: Researchers and emergency management system designers constantly find ways to produce suitable systems that have best fit between technology, and tasks. However, there is significant gap in the literature on designing information system that places greater emphasis on situational qualities. We posit that situational qualities are as important as information system success qualities such as system quality, information/knowledge quality and service quality. This research work aimed to fill this theoretical gap in designing IS for disaster management and to contribute towards guiding design decisions for future emergency management information systems development. A prototype system called CEMAS was designed and developed to support current challenges in disaster management. The underlying guiding theory for CEMAS was situational qualities interweaved within information system success factors in the form of knowledge management system. This paper presents the evaluation results of CEMAS in a simulated environment for flood.

Abstract: The first three days after an earthquake disaster demand good decisions in a very complex environment. Members of emergency operation centres (EOC) have to make decisions with limited information and under high time pressure. But the first 72 hours of disaster response activities are essential to minimize loss of life. Within the interdisciplinary German Collaborative Research Center 461: “Strong Earthquakes: A Challenge for Geosciences and Civil Engineering” a so-called Disaster Management Tool (DMT) is under development which presents some ideas for appropriate solutions to this problem. One module of the DMT will provide decision-support for the members of an EOC based on the Recognition-Primed Decision (RPD) model, a description of the decision-making process of persons in real-world settings. Options for a reasonable computer-based decision support for the RPD process will be discussed. For this the system combines a simulation of the disaster environment with a multi-agent system (MAS). The simulation shows the results of different decisions so the decision-makers can evaluate them. The MAS calculates a solution for optimal resource allocation taking into account current available information. The goal of the ongoing work is to integrate these instruments into a user-friendly interface considering the real life needs of decision-makers in an EOC.

Abstract: Fast and effective disaster management requires access to a multitude of heterogeneous, distributed, and quickly changing data sets, such as maps, satellite images, or governmental databases. In the last years, also the information created by affected persons on web sites such as flickr.com or blogger.com became an important and very quickly adapting source of information. We developed HUODINI, a prototype system for the flexible integration and visu-alization of heterogeneous data sources for disaster management. HUODINI is based on Semantic Web technologies, and in particular RDF, to offer maximal flexibility in the types of data sources it can integrate. It supports a hybrid push/pull approach to cater for the requirements of fast-changing sources, such as news feeds, and maximum performance for querying the integrated data set. In this paper, we describe the design goals underlying our approach, its architecture, and report on first experiences with the system.

Abstract: One of the most important and costly aspects of recovery operations is debris collection and disposal. The unique nature of disaster debris and the extreme amounts generated as a result of the disaster event create challenges for decision makers that are not typically encountered during every day solid-waste disposal operations. This work-in-progress research is aimed at identifying the unique aspects of disaster debris disposal and the need for decision support, which addresses these unique aspects, to assist emergency management coordinators with allocating resources during on-going debris cleanup operations. We will present a decision support system framework, discuss aspects of the knowledge base, model base, and user interface, and show how an emergency management coordinator might use the system during ongoing daily operations using real-world data from a 2003 Atlantic hurricane.

Abstract: This paper discusses the applicability of Cooperating Smart Spaces in the disaster management realm and their potential to increase the efficiency and effectiveness of rescue relief teams. The Cooperating Smart Space is a novel concept that combines and extends pervasive computing and social computing to support smart space management and community collaboration. Based on an analysis of current practice, we illustrate how the concept can be exploited in the assessment of a disaster scenario in order to improve information management, collaboration between expert teams and cooperation with online volunteers outside of the disaster zone. We present the results of an initial user evaluation by disaster management experts and conclude with important implications for the design of a Cooperating Smart Space platform. © 2012 ISCRAM.

Abstract: In this work we present a general framework for process-oriented coordination and collaboration in humanitarian operations. Process management has been proven useful in many business domains, but humanitarian operations and disaster response management in general require different process management approaches. Related work has only recently introduced traditional process management approaches for emergency management. These traditional approaches have several limitations with respect to the domain of humanitarian operations and disaster management. Our approach points to design, run-time and monitoring of inter-organizational humanitarian logistics processes. It consists of two parts: A reference model for humanitarian logistics tasks and a system for ad-hoc process management of these tasks. We discuss how they can be integrated to provide additional benefits.

Abstract: This practitioner paper outlines some of the benefits for the use of social media, from the perspective of a local-level or county-level emergency manager (EM). As compared to state and national level emergency management, because local level EMs have limited manpower and resources, social media can positively or negatively impact the effectiveness of communication before, during and after disaster strikes. Outlined in this paper are six key points where local EMs have specific needs that could be addressed by the effective use of social media and, in the opinion of the authors, represent the top issues that EMs face when considering how to leverage Twitter, Facebook, YouTube, Instagram and other social media platforms. The six needs addressed in this paper include: 1) Best practices for general social media use by EMs, 2) Social media use for internal command and control within the EM group, 3) Developing situation awareness by monitoring social media, especially prior to predicable events, 4) Communicating disaster preparedness messages through social media, 5)Using social media for gathering damage assessment information during, or immediately following a crisis,and 6) Leveraging social media volunteer groups. This short paper picks up where the Federal Emergency Management Agency's social media training leaves off and attempts to represent these six needs as use cases for researchers and developers to address in future publications and products.

Abstract: Despite the growing awareness of the untapped potential of the affected population in a disaster situation, their inclusion in a disaster management is extremely limited. This study aims to survey the literature to see whether utilizing the affected people and prevalent mobile technology can be used during disaster response. The idea is to provide the affected with a way to lead themselves to safety and empower them to serve as distributed active sources of information. This way, those people will reach safety by themselves, while at the same time helping to construct a clear image of the disaster situation without burdening the already overwhelmed emergency services. This study examines knowledge derived from disaster sociology, draws on experience from recent disasters, and extrapolates current technological solutions. By establishing that such a solution is feasible, it offers a basis for empirical studies on a mobile technology that can be used during disaster response. © 2012 ISCRAM.

Abstract: The OSIRIS project addresses the disaster management workflow in the phases of risk monitoring and crisis management. Risk monitoring allows the continuous observation of endangered areas combined with sensor deployment strategies. The crisis management focuses on particular events and the support by sensor networks. Four complementary live demonstrations will validate the OSIRIS approach. These demonstrations include water contamination, air pollution, south European forest fire, and industrial risk monitoring. This paper focuses on the latter scenario: the industrial risk monitoring. This scenario offers the special opportunity to demonstrate the relevance of OSIRIS by covering all the aspects of monitoring, preparation and response phases of both environmental risk and crisis management. The approach focuses on non-restrictive linking in a wireless sensor network in order to facilitate the addition and removal of nodes providing open interaction primitives allowing the comfortable integration, exclusion, and modification. A management layer with an event-triggered and service-based middleware is proposed. A live lab with real fire is illustrated.