|
Andreas Meissner, Zhou Wang, Wolfgang Putz, & Jan Grimmer. (2006). MIKoBOS-a mobile information and communication system for emergency response. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 92–101). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: The role of communication and information provision in coping with natural and man-made disasters and emergency situations is becoming increasingly important. In this paper we present an integrated mobile information and communication system, MIKoBOS, for emergency response operations that enables reliable data communication within the emergency site as well as between the site and the headquarters. It provides the responsible personnel involved in the emergency operation at different levels with anytime-anywhere access to relevant information. Compared to traditional voice-dominated approaches, the proposed system can greatly improve the effectiveness and efficiency of communication and coordination during disaster relief operations. Promising experimental performance results are provided for use with a number of terrestrial and satellite networks.
|
|
|
David F. Merrick, & Tom Duffy. (2013). Utilizing community volunteered information to enhance disaster situational awareness. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 858–862). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Social media allows the public to engage in the disaster response and recovery process in new and exciting ways. Many emergency management agencies in the United States are embracing social media as a new channel for alerts, warnings, and public outreach, but very few are mining the massive amounts of data available for use in disaster response. The research reflected in this paper strives to help emergency management practitioners harness the power of community volunteered information in a way that is still novel in most parts of the country. Field verification and research combined with survey results attempts to identify and solve many of the barriers to adoption that currently exist. By helping practitioners understand the virtues and limitations of this type of data and information, this research will encourage the use of community volunteered information in the emergency operations center.
|
|
|
Torbjørg Meum, & Bjørn Erik Munkvold. (2013). Information infrastructure for crisis response coordination: A study of local emergency management in norwegian municipalities. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 84–88). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: While great progress is made in terms of development and implementation on new ICT services for supporting crisis response coordination, the challenge remains on how to integrate these services within the ICT infrastructure in daily use by emergency responders. We report from an ongoing analysis of existing crisis response infrastructure in Norwegian municipalities, presenting an overview of current practice and related challenges. We argue for an information infrastructure perspective on the integration challenges, focusing on how new services based on geographic information systems and social media should be based on existing systems in use.
|
|
|
Torbjørg Træland Meum. (2014). An action design research approach to developing emergency management systems. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 175–179). University Park, PA: The Pennsylvania State University.
Abstract: We propose Action Design Research (ADR) as an approach to promote user participation and mutual learning in the design and development of systems for emergency management based on social media technologies. We outline some design challenges related to the dynamic and evolving nature of social media, and emphasize an iterative design process that is strongly oriented toward collaboration and change involving both the researcher and the user community. In particular, we emphasize the transformative power of social media and argue for design approaches that take into account the new dimension of e-participation throughout the design process.
|
|
|
Michael R. Bartolacci, Albena Mihovska, & Dilek Ozceylan Aubrecht. (2013). Optimization modeling and decision support for wireless infrastructure deployment in disaster planning and management. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 674–677). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Natural disasters and emergencies create the need for communication between and among the affected populace and emergency responders as well as other parties such as governmental agencies and aid organizations. Such communications include the dissemination of key information such as evacuation orders and locations of emergency shelters. In particular, the coordination of efforts between responding organizations require additional communication solutions that typically rely heavily on wireless communications to complement fixed line infrastructure due to the ease of use and portability. While the deployment of temporary mobile networks and other wireless equipment following disasters has been successfully accomplished by governmental agencies and network providers following previous disasters, there appears to be little optimization effort involved with respect to maximizing key performance measures of the deployment or minimizing overall cost to deploy. This work does not focus on the question of what entity will operate the portable base stations or wireless equipment utilized during a disaster, only the question of optimizing placement for planning and real time management purposes. This work examines current wireless network optimization models and points out that none of them include the necessary variables for a disaster planning or emergency deployment context. Due to the fact that the choice of wireless technology impacts the nature of an overall model, a brief discussion of exemplar wireless technologies is included. The work also proposes criteria that must be taken into account in order to have a useful model for deployment of mobile base stations and related wireless communications equipment.
|
|
|
Jyoti Laxmi Mishra, David K. Allen, & Alan D. Pearman. (2011). Activity Theory as a methodological and analytical framework for information practices in Emergency Management. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Emergency situations are chaotic in nature. It is however, necessary to understand the context in which Emergency Responders work such that information practice issues can be highlighted and addressed by the system designers. In this paper, Activity Theory is proposed as a methodological and analytical framework to study information practices in the context of Emergency Management. Activity Theory aids in achieving a holistic approach to understanding the work activities context unlike some other analytical methodologies, as it focuses on use of artifacts for the interaction of humans with their environment. In this paper, an activity system model is used to investigate information practice issues of response phase of the emergency services in the UK. Using Activity Theory as an analytical framework, several tensions and contradictions emerged which keep the system unstable but which are also a source of innovation. It is also argued that Activity Theory can usefully be applied to the analysis of information practices over short period of time.
|
|
|
Stella Moehrle. (2012). Generic self-learning decision support system for large-scale disasters. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Large-scale disasters, particularly failures of critical infrastructures, are exceptional situations which cannot be solved with standard countermeasures. The crises are complex and the decision makers face acute time pressure to respond to the disaster. IT based decision support systems provide potential solutions and assist the decision making process. Many decision support systems in emergency response and management concentrate on one kind of disaster. Moreover, complex structures are modeled and recommendations are made rule-based. This work in progress paper describes the first steps towards the development of a generic and self-learning decision support system. The methodology used is case-based reasoning. The paper concludes with a sample emergency decision process. © 2012 ISCRAM.
|
|
|
Stella Moehrle. (2013). Modeling of countermeasures for large-scale disasters using high-level petri nets. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 284–289). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: In order to support decision-making in large-scale disasters, IT-based decision support systems provide appropriate countermeasures to respond to the event. For the implementation of measures, logical and temporal dependencies have to be considered. Furthermore, factors influencing the choice of measures should be taken into account. This paper presents a generic approach to modeling sequences of countermeasures using Highlevel Petri Nets including information about the influencing factors and endangered objects. Moreover, an approach to combining several nets is proposed, which establish new sequences for recommendation. The research is part of the development of a generic decision support system for large-scale disasters. Consequently, the focus is on modeling in a generic manner and on automatic processing.
|
|
|
Stella Moehrle. (2014). On the assessment of disaster management strategies. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 215–219). University Park, PA: The Pennsylvania State University.
Abstract: Decision support systems can recommend strategies for disaster management, which can be further discussed by decision-makers. To provide rationales for the recommendations, the strategies need to be assessed according to relevant criteria. If several strategies are available, the criteria can be used for ranking the strategies. This paper addresses the issue concerning the choice of suitable criteria from several perspectives. The assessment integrates concepts on robustness, experience with regard to the implementation of a strategy, quantifiable ratios which can be deduced from simulations, and system-specific parameters. Objectives are to facilitate transparency with respect to the assessments, to provide a basis for discussions concerning the strategies, and to preserve adaptability and flexibility to account for the variability of disasters and users' preferences. The assessment should be used for ranking solutions gained from a case-based reasoning system and to reveal contributions of criteria values to the overall assessment.
|
|
|
Stefan Moellmann, David Braun, Hagen Engelmann, & Wolfgang Raskob. (2011). Key performance indicator based calculations as a decision support for the tactical level. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: For the planning of relief operations the duration and the necessary resources are key factors for a successful completion. Those factors, however, are difficult to estimate due to the large number of influencing factors in a complex crisis situation. This paper presents a software module that supports the planning by calculating the duration and the required resources for relief measures based on key performance indicators (KPI). It is part of a project called SECURITY2People aiming to develop the basics for an integrated disaster management system. The module consists of an easy to use tool to calculate the timing of a relief measure when applied to a given disaster site. In addition it contains a detailed view to display and edit the model of the selected measure which is depicted as a Gantt chart and forms the basis of the calculation. Finally, the paper describes how this module can benefit from interoperability with other modules of this project and existing systems and services.
|
|
|
Laura Montells, Susana Montero, Paloma Díaz, & Ignacio Aedo. (2007). Mining patterns for web-based emergency management systems. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 133–138). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Design patterns describe problems that occur recurrently, and specify the core of the solution in such a way that we can (re)use it in different contexts and applications. Although, web-based Emergency Management Systems domain is still in its nascent stages, there are design principles, real systems and design patterns from other related areas that can be a valuable source of knowledge to mine design patterns. From these sources we have created a patterns catalogue to assist novice designers on discovering what issues should be addressed to develop useful and successful systems. In this paper, we present the mining process and some patterns as example.
|
|
|
Sung Pil Moon, Yikun Liu, Steven O. Entezari, Afarin Pirzadeh, Andrew Pappas, & Mark Pfaff. (2013). Top health trends: An information visualization tool for awareness of local health trends. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 177–187). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: We developed an intelligent information visualization tool to enable public health officials to detect healthrelated trends in any geographic area of interest, based on Twitter data. Monitoring emergent events such as natural disasters, disease outbreaks, and terrorism is vital for protecting public health. Our goal is to support situation awareness (SA) for personnel responsible for early detection and response to public health threats. To achieve this goal, our application identifies the most frequently tweeted illnesses in a ranked chart and map for a selected geographic area. Automated processes mine and filter health-related tweets, visualize changes in rankings over time, and present other keywords frequently associated with each illness. User-centered visualization techniques of monitoring, inspecting, exploring, comparing and forecasting supports all the three stages of SA. An evaluation conducted with experts in health-related domains provided significant insights about awareness of localized health trends and their practical use in their daily work.
|
|
|
Adriaan ter Mors, Jeroen M. Valk, & Cees Witteveen. (2005). An event-based task framework for disaster planning and decision support. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 151–153). Brussels: Royal Flemish Academy of Belgium.
Abstract: Because of the apparent ineffectiveness of current disaster plans, we focus our research on modeling emergency response activities. If we can capture the crucial concepts of emergency response in a mathematical framework and apply this framework to construct disaster plans, then we pave the way for the development of automated decisions support systems for emergency response.
|
|
|
Mitchell L. Moss, & Anthony M. Townsend. (2006). Disaster forensics: Leveraging crisis information systems for social science. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 305–312). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: This paper contributes to the literature on information systems in crisis management by providing an overview of emerging technologies for sensing and recording sociological data about disasters. These technologies are transforming our capacity to gather data about what happens during disasters, and our ability to reconstruct the social dynamics of affected communities. Our approach takes a broad review of disaster research literature, current research efforts and new reports from recent disasters, especially Hurricane Katrina and the Indian Ocean Tsunami. We forecast that sensor networks will revolutionize conceptual and empiricial approaches to research in the social sciences, by providing unprecedented volumes of high-quality data on movements, communication and response activities by both formal and informal actors. We conclude with a set of recommendations to designers of crisis management information systems to design systems that can support social science research, and argue for the inclusion of post-disaster social research as a design consideration in such systems.
|
|
|
Willem J. Muhren, & Bartel A. Van De Walle. (2009). Sensemaking and information management in humanitarian disaster response: Observations from the TRIPLEX exercise. In S. J. J. Landgren (Ed.), ISCRAM 2009 – 6th International Conference on Information Systems for Crisis Response and Management: Boundary Spanning Initiatives and New Perspectives. Gothenburg: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The United Nations Disaster Assessment and Coordination (UNDAC) system is designed to assist the United Nations in providing information during the first phase of a sudden-onset emergency and in the coordination of incoming international relief at the site of the emergency. In the immediate aftermath of such an emergency, the UNDAC team will set up an On-Site Operations Coordination Centre (OSOCC) from where the operational activities of the humanitarian organizations responding to the emergency are coordinated. Information management is a key aspect in this phase as the information gathering, processing, and disseminating activities will determine the timeliness and appropriateness of the response by the international humanitarian community. Through participatory observation in the international humanitarian “TRIPLEX” exercise we explore how information managers in the OSOCC make sense of the disaster, how the immediate needs are assessed, and discuss how information systems could improve Sensemaking in these activities.
|
|
|
Willem J. Muhren, Damir Durbic, & Bartel A. Van De Walle. (2010). Exploring decision-relevant information pooling by humanitarian disaster response teams. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: It is a well-known fact that a lack of information will lead to suboptimal decisions. But even when actors jointly have all the information they need to make a well-informed decision, they may fail to find a superior alternative. This hidden profile paradigm would cause misrepresentations of crisis situations and lead to ineffective response. In this research-in-progress paper, we present the first stage of our experimental study on group decision making in humanitarian disaster response, in which we want to find out how teams can be supported to share more information, make better sense, and ultimately avoid such misrepresentations of crisis situations. First results reveal that humanitarian disaster response teams are able to share significantly more information if they would make use of more advanced information and communication systems. However, none of the teams in the experimental setup managed to find the optimal decision.
|
|
|
Aibek Musaev, De Wang, & Calton Pu. (2014). LITMUS: Landslide detection by integrating multiple sources. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 677–686). University Park, PA: The Pennsylvania State University.
Abstract: Disasters often lead to other kinds of disasters, forming multi-hazards such as landslides, which may be caused by earthquakes, rainfalls, water erosion, among other reasons. Effective detection and management of multihazards cannot rely only on one information source. In this paper, we evaluate a landslide detection system LITMUS, which combines multiple physical sensors and social media to handle the inherent varied origins and composition of multi-hazards. LITMUS integrates near real-time data from USGS seismic network, NASA TRMM rainfall network, Twitter, YouTube, and Instagram. The landslide detection process consists of several stages of social media filtering and integration with physical sensor data, with a final ranking of relevance by integrated signal strength. Applying LITMUS to data collected in October 2013, we analyzed and filtered 34.5k tweets, 2.5k video descriptions and 1.6k image captions containing landslide keywords followed by integration with physical sources based on a Bayesian model strategy. It resulted in detection of all 11 landslides reported by USGS and 31 more landslides unreported by USGS. An illustrative example is provided to demonstrate how LITMUS' functionality can be used to determine landslides related to the recent Typhoon Haiyan.
|
|
|
Thomas Münzberg, Ulrich Berbner, Tina Comes, Hanno Friedrich, Wendelin Groß, Hans-Christian Pfohl, et al. (2013). Decision support for critical infrastructure disruptions: An integrated approach to secure food supply. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 312–316). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Supplies of food and water are essential in disaster management, particularly in the very early chaotic phases when demand and available resources are highly uncertain, information systems are disrupted, and communication between communities, food suppliers, retail and emergency authorities is difficult. As many actors and organisations are involved in ever more complex food supply chains, cooperation and collaboration are vital for efficient and effective disaster management. To support decision-makers facing these problems, this paper introduces a scenario-based approach that integrates simulation of disruptions in food supply chains, and qualitative expert assessment to develop consistent scenarios that show the consequences of different strategies. To choose the best individual measures for all relevant actors and to compare it with the best overall strategy approaches from multi-criteria decision analysis are used.
|
|
|
Ahmed Nagy, & Jeannie Stamberger. (2012). Crowd sentiment detection during disasters and crises. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Microblogs are an opportunity for scavenging critical information such as sentiments. This information can be used to detect rapidly the sentiment of the crowd towards crises or disasters. It can be used as an effective tool to inform humanitarian efforts, and improve the ways in which informative messages are crafted for the crowd regarding an event. Unique characteristics of microblogs (lack of context, use of jargon etc) in Tweets expressed by a message-sharing social network during a disaster response require special handling to identify sentiment. We present a systematic evaluation of approaches to accurately and precisely identify sentiment in these Tweets. This paper describes sentiment detection expressed in 3698 Tweets, collected during the September 2010, San Bruno, California gas explosion and resulting fires. The data collected was manually coded to benchmark our techniques. We start by using a library of words with annotated sentiment, SentiWordNet 3.0, to detect the basic sentiment of each Tweet. We complemented that technique by adding a comprehensive list of emoticons, a sentiment based dictionary and a list of out-of-vocabulary words that are popular in brief, online text communications such as lol, wow, etc. Our technique performed 27% better than Bayesian Networks alone, and the combination of Bayesian networks with annotated lists provided marginal improvements in sentiment detection than various combinations of lists. © 2012 ISCRAM.
|
|
|
Martijn Neef, Kees Van Dongen, & Marijn Rijken. (2013). Community-based comprehensive recovery: Closing collaboration gaps in urban disaster recovery. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 546–550). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Disaster recovery in urban environments is a complex process. Because of high population densities and the presence of many societal and infrastructural dependencies, urban areas are prone to severe loss of self-reliance in case of a disaster. Rebuilding such areas to a self-sustaining state is a daunting task, and requires a high degree of community effort and comprehensive knowledge about the affected environment. All too often, these requirements are not properly met, leading to a long recovery trajectory and misalignments between recovery efforts and community needs. We suggest that most issues in disaster recovery stem from 'collaboration gaps': Flawed organisational structures between stakeholder parties that exist between levels of operation and between phases in the recovery process. We introduce two innovation pathways to close these gaps, and present the COBACORE project that will explore these pathways, and create a collaborative platform for effective community-based comprehensive disaster recovery.
|
|
|
Christian Neuhaus, Mario Hannappel, Daniela Giebel, & Sabine Färfers. (2012). Crisis management systems in Germany – A status report about the current functions and developments of private and public crisis managementsystems in Germany. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Crisis management systems play a critical role in supporting responders and decision makers in their crisis and emergency management functions. Even though these systems and solutions have been broadly adopted in private and public organizations, very few quantitative studies can be found on their functions, user groups, targeted stakeholders, their technological requirements and their scope of services. The present study gives an outline of our ongoing project and an insight in the first results of a three-year study of crisis management systems in Germany. The study will outline the methods of our analysis and will present some results from an analysis of over more than 170 systems from over 70 vendor/developers. It will then give a conclusion of the results and outline open and future questions. © 2012 ISCRAM.
|
|
|
Christine M. Newlon, Mark Pfaff, Himalaya Patel, Gert-Jan De Vreede, & Karl MacDorman. (2009). Mega-collaboration: The Inspiration and development of an interface for large-scale disaster response. In S. J. J. Landgren (Ed.), ISCRAM 2009 – 6th International Conference on Information Systems for Crisis Response and Management: Boundary Spanning Initiatives and New Perspectives. Gothenburg: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The need to gather and use decentralized information and resources in responding to disasters demands an integrated interface that can support large-scale collaboration. This paper describes the development of a collaboration tool interface. The tool will surpass existing groupware and social networking applications, providing easy entry, categorization, and visualization of masses of critical data; the ability to form ad-hoc teams with collaboration protocols for negotiated action; and agent-augmented mixed-initiative tracking and coordination of these activities. The paper reports user testing results concerning the data entry interface, emergent leadership, and the directed negotiation process. The paper also discusses planned enhancements, including formalized collaboration engineering and the use of a disaster simulation test bed.
|
|
|
Cynthia Nikolai, Irma Becerra-Fernandez, Troy Johnson, & Greg Madey. (2010). Leveraging WebEOC in support of the Haitian relief effort: Insights and lessons learned. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The magnitude seven earthquake that rocked Haiti has been a devastating disaster for the small country (USGS 2010). They are not alone in this crisis, however. When the earthquake struck, thousands of US citizens responded by donating money, resources, people, and time to aid in the disaster relief. To respond to the incident and to create a secure information-sharing environment, the Florida Miami-Dade County and State Emergency Operations Centers (EOC) were activated. The main information system in use at the Miami-Dade EOC is WebEOC, a web-based crisis information management system that aids in secure coordination and collaboration among EOC staff, liaisons, and emergency managers. As a result of the earthquake response efforts using this system, we have identified seven main insights and lessons learned with respect to crisis information management software. In this paper, we discuss Miami-Dade's role in the Haitian relief efforts and how this lead to these insights and lessons learned.
|
|
|
Nilani Algiriyage, Rangana Sampath, Raj Prasanna, Kristin Stock, Emma Hudson-Doyle, & David Johnston. (2021). Identifying Disaster-related Tweets: A Large-Scale Detection Model Comparison. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 731–743). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media applications such as Twitter and Facebook are fast becoming a key instrument in gaining situational awareness (understanding the bigger picture of the situation) during disasters. This has provided multiple opportunities to gather relevant information in a timely manner to improve disaster response. In recent years, identifying crisis-related social media posts is analysed as an automatic task using machine learning (ML) or deep learning (DL) techniques. However, such supervised learning algorithms require labelled training data in the early hours of a crisis. Recently, multiple manually labelled disaster-related open-source twitter datasets have been released. In this work, we create a large dataset with 186,718 tweets by combining a number of such datasets and evaluate the performance of multiple ML and DL algorithms in classifying disaster-related tweets in three settings, namely ``in-disaster'', ``out-disaster'' and ``cross-disaster''. Our results show that the Bidirectional LSTM model with Word2Vec embeddings performs well for the tweet classification task in all three settings. We also make available the preprocessing steps and trained weights for future research.
|
|
|
Tracey L. O'Sullivan, Wayne Corneil, Craig E. Kuziemsky, & Daniel E. Lane. (2013). Citizen participation in the specification and mapping of potential disaster assets. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 890–895). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Asset-mapping is a strategy used in disaster preparedness planning, however participation is typically limited to a small number of organizations with specific expertise related to disaster response. Broader strategies are needed to ensure identification of assets is comprehensive and to stimulate innovative thinking about which attributes of a community are potential assets for response and recovery. As part of The EnRiCH Project intervention, asset-mapping was used as a collaborative activity to promote identification of a broad range of assets which could be used to enhance resilience and promote preparedness among high risk populations. In this paper we present a study (in progress) which explores innovation and empowerment among a collaborative community group in Canada. Qualitative content analysis was used to analyze focus group transcripts from 2 sessions where the participants (n=18) learned how to use google docs and create a database of community assets, while developing collaborative relationships.
|
|