Huge amounts of data generated on social media during emergency situations is regarded as a trove of critical information. The use of supervised machine learning techniques in the early stages of a... Show More

Huge amounts of data generated on social media during emergency situations is regarded as a trove of critical information. The use of supervised machine learning techniques in the early stages of a crisis is challenged by the lack of labeled data for that event. Furthermore, supervised models trained on labeled data from a prior crisis may not produce accurate results, due to inherent crisis variations. To address these challenges, the authors propose a hybrid feature-instance-parameter adaptation approach based on matrix factorization, k-nearest neighbors, and self-training. The proposed feature-instance adaptation selects a subset of the source crisis data that is representative for the target crisis data. The selected labeled source data, together with unlabeled target data, are used to learn self-training domain adaptation classifiers for the target crisis. Experimental results have shown that overall the hybrid domain adaptation classifiers perform better than the supervised classifiers learned from the original source data.

Research on technology-assisted crisis management have been centered on tools to assist the response phase of a disaster. Through a semantic network analysis of concept relations in the titles of... Show More

Research on technology-assisted crisis management have been centered on tools to assist the response phase of a disaster. Through a semantic network analysis of concept relations in the titles of the publications, the authors found that many theoretical tools exist for disaster management but have not been operationalized to take a holistic approach toward technology for resilience. There is a lack of emphasis on the design of information and communication technologies, besides geographical information systems, to assist other phases of the crisis management cycle, particularly the preparedness and mitigation phases for resilience. By operationalizing the MOVE framework in a case study, the authors discover factors critical to the design of informatics and visualization tools to support resilience. This study concludes with a conceptual design framework “Digital Crow's Nest” to show feasibility of technology design for disaster resilience analytics using open data sources.

To strengthen the capability of societies to manage severe events, it is vital to understand what constitutes crisis management capability and how this can be assessed. The objective of this article... Show More

To strengthen the capability of societies to manage severe events, it is vital to understand what constitutes crisis management capability and how this can be assessed. The objective of this article is to explore how interorganizational crisis management capability has been assessed in the scientific literature. A systematic literature review was performed, resulting in a dataset of 83 publications. A thematic analysis resulted in nine themes of crisis management capability being identified, where interaction was the largest one. Analyses resulted in a comprehensive overview of assessment methods within the themes. The evaluation methods were mainly applied on real cases rather than exercises. The present article contributes with an increased understanding of how crisis management capability is evaluated, as well as applicability and limitations of different methodological approaches. This insight is essential in order to conduct a valid assessment of crisis management capability and design exercises that increase this capability.

Infectious diseases remain a threat to public health, requiring the coordinated action of many stakeholders. Little has been written about stakeholder participation and approaches to sharing... Show More

Infectious diseases remain a threat to public health, requiring the coordinated action of many stakeholders. Little has been written about stakeholder participation and approaches to sharing information, in dynamic contexts and under time pressure as is the case for infectious disease outbreaks. Communicable-disease specialists fear that delays in implementing control measures may occur if stakeholders are not included in the outbreak-management process. Two case studies described in this article show how the needs of stakeholders may vary with time and that early sharing of information takes priority over shared decision-making. The stakeholders itemized their needs and potential contributions in order to arrive at the collective interest of outbreak management. For this, the results suggest the potential for improvement through development of “network governance” including the effective sharing of information in large networks with varying needs. Outbreaks in which conflicting perceptions may occur among the stakeholders require particular attention.