Hossein Baharmand, & Tina Comes. (2015). A Framework for Shelter Location Decisions by Ant Colony Optimization. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: Earthquakes frequently destroy the homes and livelihoods of thousands. One of the most important concerns after an earthquake is to find a safe shelter for the affected people. Because of large numbers of potential locations, the multitude of constraints (e.g. access to infrastructures; security); and the uncertainty prevailing (e.g., number of places required) the identification of optimal shelter locations is a complex problem. Nevertheless, rapidly locating shelters and transferring the affected people to the nearest shelters are high priority in crisis situations. In this paper, we develop a framework based on Ant Colony Optimization (ACO) to support decisions-makers in the response phase. Using the same framework, we also derive recommendations for urban planning in the preparedness phase. We demonstrate our method with a case focusing on the city of Kerman, in Iran.
|
Hristo Tanev, Vanni Zavarella, & Josef Steinberger. (2017). Monitoring disaster impact: detecting micro-events and eyewitness reports in mainstream and social media. 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. 592–602). Albi, France: Iscram.
Abstract: This paper approaches the problem of monitoring the impact of the disasters by mining web sources for the events, caused by these disasters. We refer to these disaster effects as “micro-events”. Micro-events typically following a large disaster include casualties, damage on infrastructures, vehicles, services and resource supply, as well as relief operations. We present natural language grammar learning algorithms which form the basis for building micro-event detection systems from data, with no or minor human intervention, and we show how they can be applied to mainstream news and social media for monitoring disaster impact. We also experimented with applying statistical classifiers to distill, from social media situational updates on disasters, eyewitness reports from directly affected people. Finally, we describe a Twitter mining robot, which integrates some of these monitoring techniques and is intended to serve as a multilingual content hub for enhancing situational awareness.
|
Beibei Hu, Jan Hidders, & Philipp Cimiano. (2010). Towards context-based information delivery to police officers: A questionnaire-based requirements elicitation study. 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: In the area of information system design, the development of context-aware systems which can provide relevant information in a context-driven fashion to support mobile users in crisis management tasks represents a great challenge. Motivated by the fact that police officers are often overwhelmed by too much information, the goal of the MOSAIC project (a multi-officer system of agents for informed crisis control) is to support mobile police officers by a system which delivers contextualized information that is relevant to the task at hand. In order to elicit the information requirements of police officers who are involved in crisis situations, a questionnaire-based requirements elicitation study has been carried out in the context of the work described here. The results mainly shed light on the situation-specific information requirements of police officers in certain scenarios. The design requirements that follow from our study have clearly the potential to guide the design of context-based information delivery systems for users involved in critical situations such as the police officers we target. Our findings thus offer an important contribution to the field of information system design for crisis management.
|
Amanda L. Hughes. (2014). Participatory design for the social media needs of emergency public information officers. 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. 727–736). University Park, PA: The Pennsylvania State University.
Abstract: This paper describes the design, execution, and results of a participatory design workshop with emergency public information officers (PIOs). During the workshop, PIOs and researchers explored ideas and designs for supporting the social media needs of PIO work. Results indicate that PIO perceptions of social media have changed as they have learned to incorporate activities of the public into their work, yet they still struggle with issues of trust and liability. Based on workshop design activities, the paper offers a set of design recommendations for supporting the social media needs of PIO work practice such as the ability to monitor, document, and report social media activity.
|
Amanda L. Hughes, & Leysia Palen. (2009). Twitter adoption and use in mass convergence and emergency events. 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: This paper offers a descriptive account of Twitter (a micro-blogging service) across four high profile, mass convergence events-two emergency and two national security. We statistically examine how Twitter is being used surrounding these events, and compare and contrast how that behavior is different from more general Twitter use. Our findings suggest that Twitter messages sent during these types of events contain more displays of information broadcasting and brokerage, and we observe that general Twitter use seems to have evolved over time to offer more of an information-sharing purpose. We also provide preliminary evidence that Twitter users who join during and in apparent relation to a mass convergence or emergency event are more likely to become long-term adopters of the technology.
|
Fredrik Höglund, & Peter Berggren. (2010). Using shared priorities to measure shared situation awareness. 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: Shared situation awareness is hard to measure, especially in operative environments such as crisis management. In this paper the purpose is to develop a novel method to measure to what extent the team has shared situation awareness that can be used in operations. 20 two person teams participated in a study where a dynamic and evolving tactical decision-making task was solved. Shared situation awareness, shared priorities, and team performance were assessed. The results show that the shared priorities measure in this study did not relate to shared situation awareness. Several methodological concerns was identified which could have affected the results. The measure did relate to subjective ratings of cooperation which is very interesting and it is suggested that the measure captured aspects of teamwork. The shared priorities measure was easy to employ, required little preparation, and is a promising addition to team research.
|
Inga Kroener, Hayley Watson, & Julia Muraszkiewicz. (2017). Agility in crisis management information systems requires an iterative and flexible approach to assessing ethical, legal and social issues. 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. 247–255). Albi, France: Iscram.
Abstract: This paper focuses on the assessment of ethical, legal and social issues (ELSI) in relation to agile information systems in the domain of crisis management. The authors analyse the differing needs of a move from a traditional approach to the development of information systems to an agile approach, which offers flexibility, adaptability and responds to the needs of users as the system develops. In turn, the authors argue that this development requires greater flexibility and an iterative approach to assessing ELSI. The authors provide an example from the Horizon 2020 EU-funded project iTRACK (Integrated system for real-time TRACKing and collective intelligence in civilian humanitarian missions) to exemplify this move to an iterative approach in practice, drawing on the process of undertaking an ethical and privacy impact assessment for the purpose of this project.
|
Magnus Ingmarsson, Henrik Eriksson, & Niklas Hallberg. (2009). Exploring development of service-oriented C2 systems for emergency 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: Local emergency-response organizations must maximize their use of existing resources. Therefore, emergencyresponse organizations need appropriate command-and-control (C2) systems to coordinate not only their own resources, but also to take advantages of other local actors. The local nature of response coordination imposes additional challenges for the development of C2 systems. In particular, the C2 systems must support coordination across organizational boundaries at the local level. Service-oriented architectures (SOA) provide new technologies for the development of C2 systems. This approach is based on a set of loosely-coupled services offered by multiple actors rather than a single monolithic system. This work reports the result of a prototype SOA implementation that builds on a previous requirements engineering study for service-oriented C2 systems for local emergency response. The results illustrate how it is possible to develop lightweight C2 systems using state-or-the art Web and SOA technologies. However, there are still remaining organizational and maintainability challenges.
|
Iva Seto, David Johnstone, & Jennifer Campbell-Meier. (2018). Experts' sensemaking during the 2003 SARS crisis. 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. 44–55). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: This paper depicts the real-time sensemaking of experts as they worked to combat the first emerging disease of the 21st century: Severe Acute Respiratory Syndrome (SARS). Newspaper data was analysed from the 2003 SARS crisis, with a Canadian perspective, to follow the process of solving the puzzle of this emerging disease. Retrospective sensemaking is a process that is triggered by the unexpected, which leads to actors gathering information (taking action) in order to consider possible interpretations for the unexpected event. Disease outbreaks serve as sensemaking triggers, and actors engage in retrospective sensemaking to find out the factors involved in how the outbreak happened. Prospective sensemaking (future-oriented) is employed when actors work together to plan how to combat the disease. The newspaper data demonstrate that retrospective and prospective sensemaking are tethered: to make plans to combat a disease, actors first require a collectively agreed upon understanding from which they can generate possibilities for a crisis response. This paper contributes to the field by providing concepts for long-duration crisis sensemaking, as the bulk of organisational research focuses on acute crises such as wildfires, or earthquakes.
|
Jaco Appelman, Elisabeth A. M. Van De Kar, Mariëlle Hengst-Bruggeling, Josine Van De Ven, & Paul Burghardt. (2006). A service elicitation process for crisis management technologies. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 352–361). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: New information technological applications, that aim to support better professional responses to incidents and crises' are being developed at an increasing rate. We observe in almost any disaster that actions by civilians also contribute substantially to alleviation of the effects of a crisis. We are largely unaware what crisis management services would be of use to civilians under these particular circumstances; just as it is difficult for users to specify requirements for services based on novel technologies. These insights guided the design of a service elicitation approach that can be repeatedly used for different user groups. In this paper we introduce a design methodology and discuss outcomes of a first test-session. We reflect in the conclusions on improvements to the design.
|
Jacob L. Graham, & Mark B. Stephens. (2018). Analytic Decision Gaming – A Tool to Develop Crisis Response and Clinical Reasoning. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 60–68). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Emerging threats provide motivation to develop new methods for preparing the next generation of crisis responders. Bayesian theory shifts reasoning toward a probabilistic, epistemic paradigm, giving rise to Evans' revised heuristic-analytic theory. Researchers at The Pennsylvania State University use scenario-based training and the analytic decision game (ADG) to blend and implement these processes as foundational pedagogy for engaging, educating and training medical students as crisis responders and critical thinkers. The ADG scenarios vary by content and level of expertise, lending themselves readily adaptable to both crisis response preparation and the development of clinical reasoning. The ADG creates a virtual crisis requiring participants to engage in scenario management as role-players. For the past two years, medical students from the Penn State College of Medicine, in their first year of training, have participated in the ADG Lights Out scenario, testing community preparation and resilience after a wide-spread and months-long power outage.
|
James A. Reep, & Andrea Tapia. (2020). Toward an Organizational Technology Adoption Process (OTAP) for Social Media Integration in a PSAP. 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. 718–729). Blacksburg, VA (USA): Virginia Tech.
Abstract: Integration of social media in emergency response environments presents specific organizational challenges, such as lack of resources or information credibility. Additionally, there exists individual resistance to change in these environments that could potentially discourage adoption. To identify and understand these challenges, we conducted semi-structured group interviews with emergency call takers and dispatchers. We find that these PSAP operators desire participation and explanation of changes throughout the organizational change process. Participants also articulated they desired training regarding change even when not directly affected. Though change management procedures often call for these strategies, they are commonly overlooked, leaving individuals to imagine worse case scenarios that manifest as additional stress in an already stressful work environment. It is suggested that a formalized change management process which directly addresses the identified challenges within the organizational technology adoption process (OTAP) is needed in order to mitigate undue stress.
|
Jan Wendland, Christian Ehnis, Rodney J. Clarke, & Deborah Bunker. (2018). Sydney Siege, December 2014: A Visualisation of a Semantic Social Media Sentiment Analysis. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 493–506). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Sentiment Analyses are widely used approaches to understand and identify emotions, feelings, and opinion on social media platforms. Most sentiment analysis systems measure the presumed emotional polarity of texts. While this is sufficient for some applications, these approaches are very limiting when it comes to understanding how social media users actually use language resources to make sense of extreme events. In this paper, a Sentiment Analysis based on the Appraisal System from the theory of communication called Systemic Functional Linguistics is applied to understand the sentiment of event-driven social media communication. A prototype was developed to analyze Twitter data using the Appraisal System. This prototype was applied to tweets collected during and after the Sydney Siege 2014, a hostage situation in a busy café in Sydney. Because the Appraisal System is a theorised functional communication method, the results of this analysis are more nuanced than is possible with traditional polarity based sentiment analysis.
|
Jan Martin Jansen, Bas Lijnse, & Rinus Plasmeijer. (2010). Towards dynamic workflow support for crisis management. 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: Current process support technology for crisis management is often limited to either sharing of information or hard-coded process support through dedicated systems. Workflow management systems have the potential to improve crisis response operations by automating coordination aspects. Unfortunately most contemporary systems can only support static workflows, hence yielding inflexible support systems. Recent work on the use of functional programming techniques for workflow modeling has led to the development of the iTask system. It uses function combination to model dynamic data-driven processes and generates executable workflow support systems. Because of its focus on dynamic processes it appears promising for development of flexible crisis response systems. In this paper we present an initial discussion of the potential of the iTask system for crisis management applications. We give an overview of the iTask system, and discuss to what extent it meets the requirements of the crisis management domain.
|
Jaziar Radianti, Terje Gjøsæter, & Weiqin Chen. (2021). Slaying the SA Demons – Humans vs. Technology – A Content Analysis. 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. 946–958). Blacksburg, VA (USA): Virginia Tech.
Abstract: In this paper, we examine Situation Awareness (SA) and the application of Endsley's Demons of SA in different contexts and research areas and perform content analysis to examine how they are used, and to what degree they are perceived as stemming from human error or weaknesses in technology and if any suggestions for mitigation are primarily focused on the human or the technology side. Based on our findings, we propose universal design as a tool that can counter the effects of the demons of SA by improving the usability and accessibility of SA-supporting technology and thereby removing barriers to SA, rather than challenging the users to overcome not only barriers that are a result of the complexity of the situation itself, but also additional barriers that are caused by inferior and suboptimal design of the technology in use.
|
Jean-Paul Monet, Pierre Schaller, Sergio Pirone, Marc Castellnou Ribau, Stéphane Poyau, & Marc Dumas. (2020). Civil Protection in Europe: Towards a Unified Command System? Lessons Learned, Studies and Ideas About Change Management. 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. 315–325). Blacksburg, VA (USA): Virginia Tech.
Abstract: After the summer 2017 deadly wildfires in Portugal, President Juncker of the European Commission asked for “a stronger European Union (EU)”, clearly targeting civil protection management. This wish found achievement in the March 2019 guidance to establish a reserve of EU response capacities called “rescEU”, integrated into the jurisdictional basis of EU civil protection. However, the authors regret the ambition of this plan has not been fulfilled. Due to some very “European constraints” this “new deal” has introduced only small changes in terms of resources and knowledge management. In each of the past several years, climate change has brought new examples of fatal natural disasters: wildfires in Sweden, and Greece, and flash floods in Spain and France. Because of this continuous rise in disasters, and based on some lessons learned, the authors stress that it's now time to shape a project to improve European Civil Protection. The idea is to move from the already good modular system of the EU Civil Protection Mechanism to an integrated, robust, and unique European Command System, which clearly must be fully interoperable with other existing mechanisms (US ICS, UNOCHA...).
|
Jelle Groenendaal, & Ira Helsloot. (2021). Why Technology Not Always Adds Value to Crisis Managers During Crisis: The Case of The Dutch Nation-Wide Crisis Management System LCMS. 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. 936–945). Blacksburg, VA (USA): Virginia Tech.
Abstract: Technology undeniably plays an important role in supporting crisis managers to respond to crisis. However, when improperly designed or used, technology can be ineffective or even be detrimental to the crisis response. Therefore, in this paper we bring together insights from the scientific literature and identify 5 principles for the design and use of technology to aid crisis managers effectively. These principles might seem trivial but there are several examples of technology used in practice that show the opposite. To illustrate this, we use as a case study the Dutch nation-wide crisis management system LCMS which is used in the Netherlands by all safety regions and other public organizations to maintain and share a common operational picture supporting large-scale crisis management collaboration. We explain why crisis evaluations and research time and again show that LCMS has failed to add value for crisis managers during crisis by using the identified principles.
|
Jelle Groenendaal, Ira Helsloot, & Christian Reuter. (2022). Towards More Insight into Cyber Incident Response Decision Making and its Implications for Cyber Crisis Management. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 1025–1036). Tarbes, France.
Abstract: Organizations affected by a cyber-attack usually rely on external Cyber Incident Response (CIR) consultants to conduct investigations and mitigate the impact. These CIR consultants need to make critical decisions that could have major impact on their clients. This preliminary investigation aims to get a better understanding of CIR decision -making and answers the following questions: (1.) To what extent do experienced CIR consultants use a Recognition-Primed Decision (RPD) Making strategy during their work? (2.) What are the implications for cyber crisis management as well as for training and decision -making? To answer these questions, we conducted a literature review and interviewed six experienced CIR consultants using the Critical Decision Method. Our analysis reveals that CIR consultants recognize situations based on past experiences and apply a course of action that has worked effectively in the past. This course of action is mainly aimed at collecting and evaluating more data. This finding differs from other operational domains, such as the military and fire department, where recognition is usually followed immediately by action. For cyber crisis management, this means that crisis management teams should decide to what extent and in what ways they want to mitigate the risk of responding belatedly to cyber events, which could potentially lead to unnecessary data theft and sustained business disruption. Another implication is that crisis management teams should consider whether additional forensic investigations outweigh the expected benefits throughout the response process. For instance, if the likely entry-point of the attacker has been discovered, how much effort should be devoted to exclude other potential entry-points. Reflecting on the status-quo, several implications for training and decision making are provided.
|
Murray E. Jennex. (2012). Social media – Truly viable for crisis response? 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: On September 8, 2011 the Great San Diego/Southwest Blackout occurred. Approximately 5 million people were affected by this blackout. This paper explores the availability of social media following such a crisis event. Contrary to expectations, the cell phone system did not have the expected availability and as a result, users had a difficult time using social media to status/contact family and friends. This paper presents a survey exploring the use and availability of social media during the Great San Diego/Southwest Blackout event. © 2012 ISCRAM.
|
Jennings Anderson, Marina Kogan, Melissa Bica, Leysia Palen, Kenneth Anderson, Rebecca Morss, et al. (2016). Far Far Away in Far Rockaway: Responses to Risks and Impacts during Hurricane Sandy through First-Person Social Media Narratives. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: When Hurricane Sandy swept over the US eastern seaboard in October 2012, it was the most tweeted about event at the time. However, some of the most affected areas were underrepresented in the social media conversation about Sandy. Here, we examine the hurricane-related experiences and behaviors shared on Twitter by residents of Far Rockaway, a New York City neighborhood that is geographically and socioeconomically vulnerable to disasters, which was significantly affected by the storm. By carefully filtering the vast Twitter data, we focus on 41 Far Rockaway residents who offer rich personal accounts of their experience with Sandy. Analyzing their first-person narratives, we see risk perception and protective decision-making behavior in their data. We also find themes of invisibility and neglect when residents expressed feeling abandoned by the media, the city government, and the overall relief efforts in the aftermath of Sandy.
|
Jenny Marklund, & Cecilia Hull Wiklund. (2016). Learning from C2 Situations in the Field – Identifying Lessons from a Major Forest Fire in Sweden. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: In July 2014, Sweden?s full crisis response system engaged in a major operation as a small forest fire spun out of control, turning into the largest forest fire in Sweden in modern times. A number of investigations have been undertaken to understand the course of the fire and identify lessons for future crisis management. This paper presents one approach to identifying such lessons, the lessons learned process applied by the Swedish Armed Forces. The paper also highlights some of the major crisis response lessons from the fire, the most important being the failure to learn from lessons identified after previous forest fires. Results also show that the crisis response effort was negatively affected by a poor understanding of relevant actor?s competencies and resources, as well as lack of continuity in the initial chain of command, and identifies the need for national prioritization of resources at times of major crises.
|
Jens Kersten, Jan Bongard, & Friederike Klan. (2021). Combining Supervised and Unsupervised Learning to Detect and Semantically Aggregate Crisis-Related Twitter Content. 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. 744–754). Blacksburg, VA (USA): Virginia Tech.
Abstract: Twitter is an immediate and almost ubiquitous platform and therefore can be a valuable source of information during disasters. Current methods for identifying and classifying crisis-related content are often based on single tweets, i.e., already known information from the past is neglected. In this paper, the combination of tweet-wise pre-trained neural networks and unsupervised semantic clustering is proposed and investigated. The intention is to (1) enhance the generalization capability of pre-trained models, (2) to be able to handle massive amounts of stream data, (3) to reduce information overload by identifying potentially crisis-related content, and (4) to obtain a semantically aggregated data representation that allows for further automated, manual and visual analyses. Latent representations of each tweet based on pre-trained sentence embedding models are used for both, clustering and tweet classification. For a fast, robust and time-continuous processing, subsequent time periods are clustered individually according to a Chinese restaurant process. Clusters without any tweet classified as crisis-related are pruned. Data aggregation over time is ensured by merging semantically similar clusters. A comparison of our hybrid method to a similar clustering approach, as well as first quantitative and qualitative results from experiments with two different labeled data sets demonstrate the great potential for crisis-related Twitter stream analyses.
|
Jens Kersten, Jan Bongard, & Friederike Klan. (2022). Gaussian Processes for One-class and Binary Classification of Crisis-related Tweets. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 664–673). Tarbes, France.
Abstract: Overload reduction is essential to exploit Twitter text data for crisis management. Often used pre-trained machine learning models require training data for both, crisis-related and off-topic content. However, this task can also be formulated as a one-class classification problem in which labeled off-topic samples are not required. Gaussian processes (GPs) have great potential in both, binary and one-class settings and are therefore investigated in this work. Deep kernel learning combines the representative power of text embeddings with the Bayesian formalism of GPs. Motivated by this, we investigate the potential of deep kernel models for the task of classifying crisis-related tweet texts with special emphasis on cross-event applications. Compared to standard binary neural networks, first experiments with one-class GP models reveal a great potential for realistic scenarios, offering a fast and flexible approach for interactive model training without requiring off-topic training samples and comprehensive expert knowledge (only two model parameters involved).
|
Satria Hutomo Jihan, & Aviv Segev. (2013). Context ontology for humanitarian assistance in crisis response. 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. 526–535). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Massive crisis open data is not fully utilized to identify humanitarian needs because most of it is not in a structured format, thus hindering machines to interpret it automatically and process it in a short time into useful information for decision makers. To address these problems, the paper presents a method which merges ontologies and logic rules to represent the humanitarian needs and recommend appropriate humanitarian responses. The main advantage of the method is to identify humanitarian needs and to prioritize humanitarian responses automatically so that the decision makers are not overwhelmed with massive and unrelated information and can focus more on implementing the solutions. The method is implemented on real data from the Hurricane Wilma crisis. The use of the method in the hurricane Wilma crisis shows the potential abilities to identify the humanitarian needs in specific places and to prioritize humanitarian responses in real time.
|
Joanne I. White, & Leysia Palen. (2015). Participatory Mapping for Disaster Preparedness: The Development & Standardization of Animal Evacuation Maps. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: People who own animals are faced with complex decision making in evacuations. In the US, the Emergency Operations Center is often inundated with calls from animal owners who are aware they are under pre- or mandatory evacuation, but are unsure of what to do about evacuating their animals. Often animal evacuation is a highly improvised activity for owners and responders, though there is a now a general push toward streamlining procedures because of the high impact the matter of animals has on society?s welfare during times of emergency. This paper reports on the use of participatory design methods in a mapping project to support the range of people involved in animal evacuation during mass displacement events. The work provides insight into both procedures and standards for creating evacuation maps that communicate clearly with the public and across the range of emergency responders.
|