Abhish Khanal, Deepak Chand, Prakash Chaudhary, Subash Timilsina, Sanjeeb Prasad Panday, Aman Shakya, et al. (2020). Search Disaster Victims using Sound Source Localization. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 1022–1030). Blacksburg, VA (USA): Virginia Tech.
Abstract: Sound Source Localization (SSL) are used to estimate the position of sound sources. Various methods have been used for detecting sound and its localization. This paper presents a system for stationary sound source localization by cubical microphone array consisting of eight microphones placed on four vertical adjacent faces which is mounted on three wheel omni-directional drive for the inspection and monitoring of the disaster victims in disaster areas. The proposed method localizes sound source on a 3D space by grid search method using Generalized Cross Correlation Phase Transform (GCC-PHAT) which is robust when operating in real life scenario where there is lack of visibility. The computed azimuth and elevation angle of victimized human voice are fed to embedded omni-directional drive system which navigates the vehicle automatically towards the stationary sound source.
|
Adrot, A., & Aguerre, M. (2023). The Impact of conflicts on Data Sharing for Disaster Risk Reduction. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 43–53). Omaha, USA: University of Nebraska at Omaha.
Abstract: Cross-border regions are particularly exposed to hazards and require cooperation for Disaster Risk Reduction (DRR). Accordingly, multiple countries have been investing in technology and jointly innovate to share and process data against disasters. However, these countries’ capacity to share data depends on the history and the context of the border itself. Going further, conflicts between countries – may they be past, present or future – can radically question and endanger collaborative efforts to share data for DRR. This collaborative research, involving a cohort of master students and an NGO, explores the influence of conflicts on data sharing and cooperation for DRR. Still in progress, this research examines how conflicts affect data sharing and how DRR actors manage them. It is based on exploratory archive analysis of three distinct cases of cross-border DRR collaboration within the EU borders, as well as experts and actors interviewing. Preliminary findings reveal that conflicts affect DRR at three levels: i) actors, ii) interactions with DRR actors, iii) relations between local DRR actors and institutions. The expected contribution of this research is theoretical, practical and pedagogical.
|
Alexandre Ahmad, Olivier Balet, Jesse Himmelstein, Arjen Boin, Maaike Schaap, Paolo Brivio, et al. (2012). Interactive simulation technology for crisis management and training: The INDIGO project. 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: To face the urgent need to train strategic and operational managers in dealing with complex crises, we are researching and developing an innovative decision support system to be used for crisis management and interactive crisis training. This paper provides an overview of current decision-support systems, simulation software and other technologies specifically designed to serve crisis managers. These findings inform the design of a new interactive simulation technology system, where a 3D Common Operational Picture (COP) is shared between tactile digital whiteboard in the command center and mobile devices in the field. © 2012 ISCRAM.
|
Amro Al-Akkad, & Zimmermann, A. (2012). Survey: ICT-supported public participation in 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: In an increasingly networked society citizens at disaster sites utilize information and communication technology (ICT) to communicate needs or to share information. In order to understand better emergent possibilities and implications of applying ICT for supporting public participation in disasters, we surveyed 57 respondents regarding several key user aspects as perceived usefulness, socially related issues, or deployment. Surprisingly, our results show a clear tendency to use a disaster specific application instead of using everyday services as facebook or Twitter. However, such application poses the risk to loose its focus fading slowly away after once downloading it. Further study is needed to understand if these results are representative regarding public society. © 2012 ISCRAM.
|
Antony Galton, & Michael Worboys. (2011). An ontology of information for 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: The next generation of information systems for emergency management will be based on information provided by large and diverse collections of sensors, including information supplied by human volunteers. Consequently there is more than ever a need to provide solutions to the integration question, so that the Common Operating Picture can truly and effectively provide the unified view required of it. This paper describes some work on the ontology of information that can contribute to a solution of the integration problem. To set the stage, the paper discusses the relevance of information integration to emergency management, and then goes on to describe a project that provided the catalyst for this work. Later sections introduce ontological research and proceed to use it to lay the foundations for an ontology of information. In the final sections we indicate how such an ontology can be used in the context of emergency management.
|
Art Botterell, & Martin Griss. (2011). Toward the next generation of emergency operations systems. 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 more than half a century the Emergency Operations Center (EOC) has been a key component of emergency management (EM), homeland security and business continuity practice. Changes in the technical, threat, economic and social environments are placing new pressures on the concept of the EOC in the public, private and community sectors. Investigation of the desirable attributes of a “Next Generation EOC” has led to alternative EOC roles and configurations. This paper describes emerging pressures on, and trends in, emergency and business contingency management systems, and describes a research program to explore solutions to both new and persistent design challenges.
|
Bjørn Erik Munkvold, Jaziar Radianti, Jan Ketil Rød, Tomasz Opach, Mikael Snaprud, Sofie Pilemalm, et al. (2019). Sharing Incident and Threat Information for Common Situational Understanding. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: This paper presents the INSITU research project initiated to provide a systematic approach for effective sharing, integration and use of information from different sources, to establish a common operational picture (COP) and shared situational understanding among multiple actors in emergency response. The solution developed will provide an interactive map display, integrating harmonisation of terminology and collaboration support for information sharing and synthesis. The enhanced COP will also support evaluation and learning from exercises and incidents. The project involves close collaboration with emergency management stakeholders in Norway, for requirements analysis, participatory design, and validation of project deliverables. The research will improve information sharing and decision support in emergency operations centres, which will contribute to improve societal resilience through more effective response capability.
|
Christoph Amelunxen, & Janina Isabella Sander. (2019). Information collection using process visualisation in the risk management concept for emergency response. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Security-critical processes of emergency response are part of a complex system of people, organisation and
technology. They are often characterised by their own dynamics, interconnectedness and information deficits. In
addition, a wide variety of stakeholders, some from different organisations, work together, each specialising in a
specific area. In order to capture this (process-) knowledge in risk management, information from the experts is
necessary. However, experts are difficult to access, often separated locally, cost-intensive and usually have little
time (discussion-) capacity. A pictogram-based process visualisation was developed within the risk management
concept. The method could be validated within a European project in an expert workshop. This was done using
the example of a CBRN mass casualty incident. By using the methods presented, very good qualitative and
quantitative results can be achieved from the perspectives of various organisations and their experts. The limited
resource ?expert? is used optimally.
|
Christoph Markmann, Heiko A. Von Der Gracht, Jonas Keller, & Rixa Kroehl. (2012). Collaborative foresight as a meansto face future risks – An innovative platform conception. 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: Increasing market volatility and disruptions imply risks for companies and governments and have become therefore focus topics. Adequate tools to identify, assess and manage future developments are key to survive in a turbulent environment. In our paper, we present the systematic development process of an innovative, web-based foresight platform, which is a joint research project funded by the German Federal Government and aims to improve the robustness in decision making by collaborative foresight. Its four interlinked applications have the purpose to enable their users a collaborative generation, discussion, evaluation and development of future-oriented knowledge. Thereby, a special emphasis is on the relevance and the timeliness of the provided information. Within the multi-stage requirement analysis of the tool platform we analyzed existing concepts in order to identify strengths and weaknesses and conducted brainstorming sessions and interviews with professionals of 130 companies and organizations to account for different backgrounds, perspectives and intentions. © 2012 ISCRAM.
|
Christopher W. Zobel, Stanley E. Griffis, Steven A. Melnyk, & John R. MacDonald. (2012). Characterizing disaster resistance and recoveryusing outlier detection. 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: Most definitions of disaster resilience incorporate both the capacity to resist the initial impact of a disaster and the ability to recover after it occurs. Being able to characterize and analyze resilient behavior can lead to improved understanding not only of the capabilities of a given system, but also of the effectiveness of different strategies for improving its resiliency. This paper presents an approach for quantifying the transient behavior resulting from a disaster event in a way that allows researchers to not only describe the transient response but also assess the impact of various factors (both main and interaction effects) on this response. This new approach combines simulation modeling, time series analysis, and statistical outlier detection to differentiate between disaster resistance and disaster recovery. Following the introduction of the approach, the paper provides a preliminary look at its relationship to the existing concept of predicted disaster resilience. © 2012 ISCRAM.
|
Claire Laudy. (2017). Rumors detection on Social Media during Crisis Management. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 623–632). Albi, France: Iscram.
Abstract: Social Media monitoring has become a major issue in crisis and emergencies management. Indeed, social media may ease the sharing of information between citizens and Public Safety Organizations, but it also enables the rapid spreading of inaccurate information. As information is now provided and shared by anyone to anyone, information credibility is a major issue. We propose an approach to detect rumor in social media. This paper describes our work on semantic graph based information fusion, enhanced with uncertainty management capabilities. The uncertainty management capability enables managing the dierent level of credibility of actors of an emergency (dierent PSO oÿcers and citizens). Functions for information synthesis, conflicting information detection and information evaluation were developed and test during experimentation campaigns. The synthesis and conflicting information detection functionalities are very welcome by end-users. However, the uncertainty management is a combinatorial approach which remains a limitation for use with large amount of information.
|
David J. Saab, Edgar Maldonado, Razvan Orendovici, Louis-Marie Ngamassi Tchouakeu, Kang Zhao, Annemijn Van Gorp, et al. (2008). Building global bridges: Coordination bodies for improved information sharing among humanitarian relief agencies. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 471–483). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Information is a critical component to improved inter-agency coordination during disaster response. Coordinated information and communication technologies deployments as well as coordinated information management processes are important tools in the provision of this information. However, multilateral agency coordination faces many challenges, which has sparked the formation of coordination bodies. This research examines three such bodies and describes their organizational arrangements as well as identifies common challenges they face to effective coordination. It finds that the bodies differ on a variety of dimensions including funding mechanisms, autonomy, and number of members, which will likely have implications for the strategies they employ. Also, the coordination bodies identify a lack of standardization, capacity and information availability and analysis as challenges to improved coordination.
|
Dennis J. King. (2006). VISTA-a visualization analysis tool for humanitarian situational awareness. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 11–16). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: The US Department of State's Humanitarian Information Unit (HIU) is developing a new product and web-based visualization analysis tool, known as VISTA (Visualized Information & Synthesized Temporal Analysis). VISTA displays geo-spatial, temporal, numerical/graphic data and textual information, all in one product or via a web interface. VISTA is primarily intended for use by decision-makers, analysts, desk/project officers, and others to provide up-to-date common operating picture ie a vista about an emergency, issue or project.
|
Duncan T. Wilson, Glenn I. Hawe, Graham Coates, & Roger S. Crouch. (2013). Scheduling response operations under transport network disruptions. 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. 683–687). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Modeling the complex decision problems faced in the coordination of disaster response as a scheduling problem to be solved using an optimization algorithm has the potential to deliver efficient and effective support to decision makers. However, much of the utility of such a model lies in its ability to accurately predict the outcome of any proposed solution. The stochastic nature of the disaster response environment can make such prediction difficult. In this paper we examine the effect of unknown disruptions to the road transport network on the utility of a disaster response scheduling model. The effects of several levels of disruption are measured empirically and the potential of using real-time information to revise model parameters, and thereby improve predictive performance, is evaluated.
|
Edjossan-Sossou, A., Selouane, K., Sayah, M. A., Ouabou, M., Vignote, C., Capitaine, M., et al. (2023). An innovative scenario-based modeling tool for the management of resilient water resources. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 808–821). Omaha, USA: University of Nebraska at Omaha.
Abstract: As freshwater availability for domestic and agro-industrial uses is highly sensitive to climate change, there is an urgent need for the management of this critical resource to be resilient, i.e., to cope with and rapidly recover from climate risks. To achieve this resilient goal, decision-makers need to have a comprehensive understanding of (i) the current and future local water resources, (ii) the ways these resources are and will be impacted by climate change, and (iii) the effects their management decisions can have. In this paper, we present an innovative scenario based modeling tool that help decision-makers make the most appropriate decision towards managing water resources: the Resilience Performance Assessment (RPA). This GIS-based decision support tool illustrates the current and future effects of climate change on local water resources and simulates the outcomes of different water resources management strategies. The RPA helps guide decision-makers towards the implementation of context specific adaptation strategies.
|
Elina Ramsell, Tobias Andersson Granberg, & Sofie Pilemalm. (2019). Identifying functions for smartphone based applications in volunteer emergency response. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Emergency response organisations struggle with resource constraints and thereby faces challenges in providing
high-quality public services. Utilising voluntary first responders is one way to address these challenges. There
are different types of volunteers who can help at an emergency site, e.g. citizen volunteers or voluntary
professionals from other occupations. To successfully engage with and utilise these resources, adequate
information and communication technology (ICT) is necessary. In this meta-study, combining and further
exploring two previous studies, the aim is to identify, analyse and evaluate suitable functions for smartphone
applications that can be used to dispatch and support volunteers. The results show that the functions can be
divided into essential ones that are necessary for the response to work at all, and others that might contribute to a
more effective response. The study also shows that the same functions can be used for different volunteer
groups.
|
Encarnación, T., & Wilks, C. R. (2023). Role of Expressed Emotions on the Retransmission of Help-Seeking Messages during Disasters. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 340–352). Omaha, USA: University of Nebraska at Omaha.
Abstract: Emergency managers rely on formal and informal communication channels to identify needs in post-disaster environments. Message retransmission is a critical factor to ensure that help-seekers are identified by disaster responders. This paper uses a novel annotated dataset of Twitter posts from four major disasters that impacted the United States in 2021, to quantify the effect that expressed emotions and support typology have on retransmission. Poisson regression models are estimated, and the results show that messages seeking instrumental support are more likely to be retransmitted. Expressions of anger, fear, and sadness increase overall retweets. Moreover, expressions of anger, anticipation, or sadness increase the likelihood of retransmission for messages that seek instrumental help.
|
Erik A.M. Borglund. (2017). The Role of Artefacts in Creating a Common Operational Picture During Large Crises. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 191–203). Albi, France: Iscram.
Abstract: This paper is about the work that takes place during large police operations in different command post settings, and how artefacts are used in the collaborative process in creating a common operational picture (COP). We apply “artefactual multiplicity” as our analytical lens. An interpretative research approach has been applied in form of ethnographical field studies using observation and informal interviews as data collection techniques. The artefacts that have been studied are definable as common artefacts, i.e. artefacts that are commonly available in our work environment. Based upon the five separate studies, the artefacts studied are found to be very important as collaborative tools and many also have embedded visualization functionalities. The main contribution from this research is 1) extensive knowledge about how the artefacts are used in the establishment of the COP during large police operations, where the process of establishing the COP is, to a very large extent, dependent upon the artefacts' collaborative and multiple functions; 2) the proposal and suggestion to study the whole staff and the artefacts used by the staff as one heterogeneous unit, as a record of activities. Studies of single artefacts in isolation reduce the possibility of seeing the full multiplicity of all the artefacts used within the staff, and the complexity of the intertwined web of artefactual functions.
|
Erik AM Borglund, & Martina Granholm. (2020). You Talk the Talk – But What Do You Talk About? In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 295–302). Blacksburg, VA (USA): Virginia Tech.
Abstract: Post-crisis analysis of transboundary crises in Sweden is problematic due to limited documentation. We believe that there is a need to find tools to better understand the command and control, and to understand how the information sharing that takes place during larger crises works. This paper presents the results of an ongoing research, as well as findings about how the TETRA system is used for information sharing in transboundary crises. The data used was collected from two large emergency exercises, where Swedish, Finnish and Norwegian TETRA systems were merged. Communication in 10 shared talk groups was recorded, transcribed and analyzed. The communication in shared TETRA-talk-groups mostly focused on information about the accident, the recourses and first respond units, as well as the actions of each unit. The research also exemplifies and shows that communication within TETRA-talk-groups in transboundary crisis can give new insight into how command and control works.
|
Erion Elmasllari. (2019). Design and development methods for improving acceptance of IT among emergency responders. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Various sources report a low adoption of IT-based tools in emergency response, as well as a negative attitude of
responders to such tools. The responders? needs, simply put, are not met by the IT-based tools offered to them.
Observing this situation through a user-centered design lens, we note that such problems typically stem from
insufficient or erroneous context analysis. The deficiencies become even more pronounced when considering that
emergency response represents a complex, adaptive socio-technical system. We also note that the appropriate
methodology for designing ER systems is rarely discussed in literature and in research papers. To fill that void, the
present paper discusses a minimal set of techniques that, both in our experience and according to state of the art
practice, can guide developers towards positively-accepted IT systems for emergency response.
|
Erion Elmasllari. (2018). Why IT systems for emergency response get rejected: examining responders' attitude to IT. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 994–1002). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Emergency responders' attitude to IT is marked by resistance, aversity, and rejection. This does not extend to technology in general and is specific to IT alone. Current research on the topic only presents partial, scattered, and unconnected accounts that do not provide a starting point on how to tackle this attitude. The available models for technology acceptance are also generic and do not take into account the specifics of the emergency response domain. Through extensive user research combined with a grounded theory approach, this paper identifies twelve problem areas from which responders' negative attitude towards IT arises. By extending the technology acceptance models with this new knowledge, we provide system designers with an understanding of what to tackle and tune in their IT system designs so that a positive attitude among emergency responders can be achieved.
|
Erion Elmasllari, & René Reiners. (2017). Learning From Non-Acceptance: Design Dimensions for User Acceptance of E-Triage Systems. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 798–813). Albi, France: Iscram.
Abstract: As of 26 December 2016, seventeen electronic triage systems for disaster triage have been proposed in the ACM, IEEE, and ISCRAM publication databases. Most of these systems have remained inside the laboratory; the rest have disappeared entirely. Responders still prefer to do triage with paper tags from the 1960's, while no research has been presented on why the proposed e-triage systems have not found acceptance and use in the field. Based on exhaustive literature research and on the findings from the four-year long, EU research project BRIDGE , this paper presents e-triage acceptance dimensions, analyzes the main reasons why proposed systems have been rejected, and guides designers towards upcoming, well-accepted e-triage systems.
|
Gaoussou Camara, Rim Djedidi, Sylvie Despres, & Moussa Lo. (2012). Towards an ontology for an epidemiological monitoring system. 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: Epidemiological monitoring systems are used to control the evolution of disease spreading and to suggest action plans to prevent identified risks. In this domain, risk prediction is based on quantitative approaches that are hardly usable when data collection is not possible. In this paper, a qualitative approach based on an epidemiological monitoring ontology is proposed. We describe the design of this ontology and show how it fits into classical monitoring systems and helps overcoming limits related to quantitative approaches. © 2012 ISCRAM.
|
Gavin Treadgold, James Gunn, Paul Morton, & Simon Chambers. (2018). Developing a regional approach and strategy for geographical information systems for emergency management. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 190–199). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: This paper outlines practitioner work-in-progress in Canterbury, New Zealand, to develop a regional approach for geographical information systems (GIS) for emergency management. This is based upon recent events in Canterbury including earthquakes, floods, and fire; as well as New Zealand-wide work that is being done under the NZ GIS4EM banner. It introduces our approach, discusses a mind map that is being used to track desired data sets, plans to develop applications to support response functions in emergency operations centres, and the goal of using the common data sets as the basis of a common operating picture for Canterbury. Risks and issues associated with this work are highlighted, and then the draft strategy is introduced with desired outcomes and principles to achieve this goal. While initial work is primarily focused on GIS, the expectation is that the approach will be expanded to take a broader information management perspective in future.
|
Guoqin Ma, & Chittayong Surakitbanharn. (2019). Predicting Hurricane Damage Using Social Media Posts Coupled with Physical and Socio-Economic Variables. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: During a natural disaster or emergency event, individual social media posts or hot spots may not necessarily correlate
to the most devastated areas. To better understand the correlation between social media and physical damage, we
compare Tweets, data about the physical environment, and socio-economic factors with insurance claim information
(as a proxy for physical damage) from 2017 Hurricane Irma in the state of Florida. We use machine learning
to identify relevant Tweets, sensitivity analyses to identify socio-economic factors, and statistical regression to
determine the predictive capability of insurance claims as a proxy for damage. We find that Tweets alone result in a
poorly fitted regression model of insurance claims, but the inclusion of physical features (e.g., power outages, wind
level) and socio-economic factors (e.g., population density, education, Internet access) improves the model?s fit.
Such models contribute to the knowledge base that may allow social media to predict damage in real-time.
|