|
Jeremy Diaz, Lise St. Denis, Maxwell B. Joseph, Kylen Solvik, & Jennifer K. Balch. (2020). Classifying Twitter Users for Disaster Response: A Highly Multimodal or Simple Approach? 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. 774–789). Blacksburg, VA (USA): Virginia Tech.
Abstract: We report on the development of a classifier to identify Twitter users contributing first-hand information during a disaster. Identifying such users helps social media monitoring teams identify critical information that might otherwise slip through the cracks. A parallel study (St. Denis et al., 2020) demonstrates that Twitter user filtering creates an information-rich stream of content, but the best way to approach this task is unexplored. A user's profile contains many different “modalities” of data, including numbers, text, and images. To integrate these different data types, we constructed a multimodal neural network that combines the loss function of all modalities, and we compared the results to many individual unimodal models and a decision-level fusion approach. Analysis of the results suggests that unimodal models acting on Twitter users' recent tweets are sufficient for accurate classification. We demonstrate promising classification of Twitter users for crisis response with methods that are (1) easy to implement and (2) quick to both optimize and infer.
|
|
|
Jonas Höchst, Lars Baumgartner, Franz Kuntke, Alvar Penning, Artur Sterz, & Bernd Freisleben. (2020). LoRa-based Device-to-Device Smartphone Communication for Crisis Scenarios. 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. 996–1011). Blacksburg, VA (USA): Virginia Tech.
Abstract: In this paper, we present an approach to facilitate long-range device-to-device communication via smartphones in crisis scenarios. Through a custom firmware for low-cost LoRa capable micro-controller boards, called rf95modem, common devices for end users can be enabled to use LoRa through a Bluetooth, Wi-Fi, or serial connection. We present two applications utilizing the flexibility provided by the proposed firmware. First, we introduce a novel device-to-device LoRa chat application that works a) on the two major mobile platforms Android and iOS and b) on traditional computers like notebooks using a console-based interface. Second, we demonstrate how other infrastructure-less technology can benefit from our approach by integrating it into the DTN7 delay-tolerant networking software. The firmware, the device-to-device chat application, the integration into DTN7, as well as the experimental evaluation code fragments are available under permissive open-source licenses.
|
|
|
Josep Cobarsí, & Laura Calvet. (2020). Community resilience instruments: Chances of improvement through customization and integration? 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. 381–388). Blacksburg, VA (USA): Virginia Tech.
Abstract: Resilience is understood as the ability of a system, community or society exposed to hazards to resist, absorb, accommodate, adapt to, transform and recover from the effects of a hazard in a timely and efficient manner. So far, dozens of measurement instruments have been developed to measure community resilience to disasters, considering each one different types of hazards (general, natural, climate, man-made, etc.) and communities (general, urban, rural, etc.). However, none of these instruments has been widely adopted yet. In this context, we discuss important gaps for resilience research and practice. Then, we propose a conceptual framework to review community resilience instruments, so to enhance their improvement through two facets (or dimensions) we propose of customization and integration. This framework is characterized by the following properties for community resilience instruments: encapsulation, intelligibility, geographical focus, hazard range focus, connectivity, adaptability to dynamic conditions, datification, and stakeholders' involvement. We look forward to apply this framework to review a purposive sample of community resilience instruments regarding natural disasters.
|
|
|
Julien Coche, Aurelie Montarnal, Andrea Tapia, & Frederick Benaben. (2020). Automatic Information Retrieval from Tweets: A Semantic Clustering Approach. 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. 134–141). Blacksburg, VA (USA): Virginia Tech.
Abstract: Much has been said about the value of social media messages for emergency services. The new uses related to these platforms bring users to share information, otherwise unknown in crisis events. Thus, many studies have been performed in order to identify tweets relating to a crisis event or to classify these tweets according to certain categories. However, determining the relevant information contained in the messages collected remains the responsibility of the emergency services. In this article, we introduce the issue of classifying the information contained in the messages. To do so, we use classes such as those used by the operators in the call centers. Particularly we show that this problem is related to named entities recognition on tweets. We then explain that a semi-supervised approach might be beneficial, as the volume of data to perform this task is low. In a second part, we present some of the challenges raised by this problematic and different ways to answer it. Finally, we explore one of them and its possible outcomes.
|
|
|
Justin Michael Crow. (2020). Verifying Baselines for Crisis Event Information Classification on Twitter. 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. 670–687). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media are rich information sources during crisis events such as earthquakes and terrorist attacks. Despite myriad challenges, with the right tools, significant insight can be gained to assist emergency responders and related applications. However, most extant approaches are incomparable, using bespoke definitions, models, datasets and even evaluation metrics. Furthermore, it's rare that code, trained models, or exhaustive parametrisation details are openly available. Thus, even confirming self-reported performance is problematic; authoritatively determining state of the art (SOTA) is essentially impossible. Consequently, to begin addressing such endemic ambiguity, this paper makes 3 contributions: 1) replication and results confirmation of a leading technique; 2) testing straightforward modifications likely to improve performance; and 3) extension to a novel complimentary type of crisis-relevant information to demonstrate it's generalisability.
|
|
|
Kamol Roy, MD Ashraf Ahmed, Samiul Hasan, & Arif Mohaimin Sadri, P. D. (2020). Dynamics of Crisis Communications in Social Media: Spatio-temporal and Text-based Comparative Analyses of Twitter Data from Hurricanes Irma and Michael. 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. 812–824). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media platforms play critical roles in information dissemination, communication and co-ordination during different phases of natural disasters as it is crucial to know the type of crisis information being disseminated and user concerns. Large-scale Twitter data from hurricanes Irma (Sept. 2017) and Michael (Oct. 2018) are used here to understand the topic dynamics over time by applying the Dynamic Topic Model, followed by a comparative analyses of the differences in such dynamics for these two hurricane scenarios. We performed a spatio-temporal analyses of user activities with reference to the hurricane center location and wind speed. The findings of spatio-temporal analyses show that differences in hurricane path and the affected regions influence user participation and social media activity. Besides, topic dynamics reveals that situational awareness, disruptions, relief action are among the patterns common for both hurricanes; unlike topics such as hurricane evacuation and political situation that are scenario dependent.
|
|
|
Konstantinos Konstantoudakis, Georgios Albanis, Emmanouil Christakis, Nikolaos Zioulis, Anastasios Dimou, Dimitrios Zarpalas, et al. (2020). Single-Handed Gesture UAV Control for First Responders – A Usability and Performance User Study. 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. 937–951). Blacksburg, VA (USA): Virginia Tech.
Abstract: Unmanned aerial vehicles (UAVs) have increased in popularity in recent years and are now involved in many activities, professional and otherwise. First responders, those teams and individuals who are the first to respond in crisis situations, have been using UAVs to assist them in locating victims and identifying hazards without endangering human personnel needlessly. However, professional UAV controllers tend to be heavy and cumbersome, requiring both hands to operate. First responders, on the other hand, often need to carry other important equipment and need to keep their hands free during a mission. This work considers enabling first responders to control UAVs with single-handed gestures, freeing their other hand and reducing their encumbrance. Two sets of gesture UAV controls are presented and implemented in a simulated environment, and a two-part user study is conducted: the first part assesses the comfort of each gesture and their intuitive association with basic flight control concepts; and the second evaluates two different modes of gesture control in a population of users including both genders, and first responders as well as members of the general populace. The results, consisting of both objective and subjective measurements, are discussed, hindrances and problems are identified, and directions of future work and research are mapped out.
|
|
|
Kristine Steen-Tveit. (2020). Identifying Information Requirements for Improving the Common Operational Picture in Multi-Agency Operations. 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. 252–263). Blacksburg, VA (USA): Virginia Tech.
Abstract: While there exists a considerable body of literature on the importance of a common operational picture (COP) in multi-agency emergency operations, the COP concept itself still lacks a univocal definition. Despite the lack of consensus regarding the mechanisms underlying the COP, the literature implies a level of consistency in the focus on sharing critical information. Based on interviews with Norwegian emergency management stakeholders, this study investigates common information requirements for emergency management services and presents an example of a framework for structuring the sharing of critical information and building a COP. Termed 'the window report', this framework is used among emergency stakeholders in Norway and Sweden. The study identified eight common information requirement categories for managing extreme weather scenarios. With a focus on common information needs and a process for structured information sharing, future strategic emergency management planning might take a more holistic perspective on cross-sectoral operations than in current practice.
|
|
|
Kristine Steen-Tveit, Jaziar Radianti, & Bjørn Erik Munkvold. (2020). SMS-based real-time data collection for evaluation of situational awareness and common operational picture: lessons learned from a field exercise. 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. 276–284). Blacksburg, VA (USA): Virginia Tech.
Abstract: Managing complex multi-agency emergency operations requires that the key actors have a holistic, correct and dynamic situational awareness (SA) and that the involved actors establish a common operational picture (COP). Establishing SA and COP are key objectives in many multi-agency exercises, however, reported research shows limitations in existing methods and approaches for collecting the data required for evaluating this. By being able to capture near real-time information during different phases of the exercise we will be better positioned to identify what works well and what does not work in the process of establishing SA and COP. Our paper presents an example of real-time data collection using SMS during a multi-agency field exercise. Overall, the results support the idea of this as an effective method for collecting real-time data for analyzing the formation of SA and a COP among actors in emergency management.
|
|
|
Lars Gerhold, Roman Peperhove, & Edda Brandes. (2020). Using Scenarios in a Living Lab for improving Emergency Preparedness. 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. 568–579). Blacksburg, VA (USA): Virginia Tech.
Abstract: Emergency preparedness and management processes are highly influenced by the use of digital technologies. Unfortunately, due to their rapid development, stakeholders from civil protection as well as policy makers often are not aware of new technological possibilities, their potentials and risks. This paper offers a methodological approach to experience evolving technologies by using scenarios in a living lab, equipped with demonstrators from recent research projects. The scenarios are presented to stakeholders from civil protection and policy making by telling a future story about the potential usage of emerging technologies. The Future Security Lab allows addressees to see, understand and use technologies that may become relevant within the next five to ten years and so a profound basis for knowledge transfer is offered. The case study “Digitalization of Emergency Preparedness 2025” demonstrates how scenarios can be used to integrate demonstrators in stories about the future of civil protection. First results of an evaluation provide positive feedback from attendees.
|
|
|
Laura Szczyrba, Yang Zhang, Duygu Pamukcu, & Derya Ipek Eroglu. (2020). A Machine Learning Method to Quantify the Role of Vulnerability in Hurricane Damage. 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. 179–187). Blacksburg, VA (USA): Virginia Tech.
Abstract: Accurate pre-disaster damage predictions and post-disaster damage assessments are challenging because of the complicated interrelationships between multiple damage drivers, including various natural hazards, as well as antecedent infrastructure quality and demographic characteristics. Ensemble decision trees, a family of machine learning algorithms, are well suited to quantify the role of social vulnerability in disaster impacts because they provide interpretable measures of variable importance for predictions. Our research explores the utility of an ensemble decision tree algorithm, Random Forest Regression, for quantifying the role of vulnerability with a case study of Hurricane Mar\'ia. The contributing predictive power of eight drivers of structural damage was calculated as the decrease in model mean squared error. A measure of social vulnerability was found to be the model's leading predictor of damage patterns. An additional algorithm, other methods of quantifying variable importance, and future work are discussed.
|
|
|
Lennart Landsberg, David Ganske, Christopher Munschauer, & Ompe Aimé Mudimu. (2020). Using Existing Data to Support Operational Emergency Response in Germany – Current Use Cases, Opportunities and Challenges. 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. 406–415). Blacksburg, VA (USA): Virginia Tech.
Abstract: The availability of resources in the fire and ambulance services in Germany is facing a radical change. Demographic and social transition is reducing the availability of volunteer personnel, and increasing traffic congestion in cities is resulting in longer travel times for emergency vehicles. This paper presents the findings of the definition phase of a research project that addresses these changes. It shows the basic idea of how resilience of fire and ambulance services can be improved by analyzing operational data from past incidents using artificial intelligence (AI). The primary objective is the development of a decision support system for control center dispatchers, which ensures optimal use of available resources. As the result of the definition phase, this paper gives an overview of existing data, current as well as future use cases and also highlights risks and challenges that have to be considered.
|
|
|
Lise Ann St. Denis, Amanda Lee Hughes, Jeremy Diaz, Kylen Solvik, Maxwell B. Joseph, & Jennifer K. Balch. (2020). 'What I Need to Know is What I Don't Know!': Filtering Disaster Twitter Data for Information from Local Individuals. 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. 730–743). Blacksburg, VA (USA): Virginia Tech.
Abstract: We report on the design, development, and evaluation of a user labeling framework for social media monitoring by emergency responders. By labeling Twitter user accounts based on behavior and content, this novel approach identifies tweets from accounts belonging to Individuals generating Personalized content and captures information that might otherwise be missed. We evaluate the framework using training data from the 2018 Camp, Woolsey, and Hill fires. Approximately 30% of the Individual-Personalized tweets contain first-hand information, providing a rich stream of content for social media monitoring. Because it can quickly eliminate most redundant tweets, this framework could be a critical first step in an end-to-end information extraction pipeline. It may also generalize more easily for new disaster events since it relies on general user account attributes rather than tweet content. We conclude with next steps for refining and evaluating our framework in near real-time during a disaster response.
|
|
|
Liuqing Li, & Edward A. Fox. (2020). Disaster Response Patterns across Different User Groups on Twitter: A Case Study during Hurricane Dorian. 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. 838–848). Blacksburg, VA (USA): Virginia Tech.
Abstract: We conducted a case study analysis of disaster response patterns across different user groups during Hurricane Dorian in 2019. We built a tweet collection about the hurricane, covering a two week period. We divided Twitter users into two groups: brand/organization or individual. We found a significant difference in response patterns between the groups. Brand users increasingly participated as the disaster unfolded, and they posted more tweets than individual users on average. Regarding emotions, brand users posted more tweets with joy and surprise, while individual users posted more tweets with sadness. Fear was a common emotion between the two groups. Further, both groups used different types of hashtags and words in their tweets. Some distinct patterns were also discovered in their concerns on specific topics. These results suggest the value of further exploration with more tweet collections, considering the behavior of different user groups during disasters.
|
|
|
Lixiong Chen, Monika Buscher, & Yang Hu. (2020). Crowding Out the Crowd:The Transformation of Network Disaster Communication Patterns on Weibo. 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. 472–489). Blacksburg, VA (USA): Virginia Tech.
Abstract: There is a surge in people turning to social media in disasters in China. In the 2010 Yushu earthquake, 5,979 Weibos were posted. Almost 10 years on, in the 2019 Yibin earthquake it was 17,495. This study presents a Social Network Analysis of the dynamics of this growth, taking the six major Chinese earthquakes of this decade as a case study. By constructing relationship matrices, the research reveals a transformation of networked crisis communication patterns on Weibo. We show how communication relationships between verified organisational users, government agencies, verified individual users (such as celebrities) and unverified ordinary users have changed, and we observe that government agencies are 'crowding out the crowd' of other users. We consider key aspects and the ethical complexities of this phenomenon.
|
|
|
Louis Ngamassi, Thiagarajan Ramakrishnan, & Shahedur Rahman. (2020). Investigating the Use of Social Media by Underserved Communities for Disaster 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. 490–496). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media is emerging as a communication tool for successfully managing disasters. However, studies have shown that not all individuals are equally predisposed towards effectively using social media for disaster management. There still exists a big digital divide when it comes to using social media for disaster management. Drawing on situational theory of problem solving, we develop a conceptual model that examines the motivating factors for the underserved communities to use social media for disaster management. We further develop and cross-validate a questionnaire instrument to acilitate empirical research. We thus offer an empirical context for motivating individuals from underserved communities to use social media effectively during disasters.
|
|
|
Manon Grest, Matthieu Lauras, & Benoit Montreuil. (2020). A Humanitarian Supply Chain Maturity Model. 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. 613–621). Blacksburg, VA (USA): Virginia Tech.
Abstract: Over the past decades, humanitarian organizations have largely been criticized for their lack of effectiveness regarding their mission of assisting vulnerable population. However, few researches have investigated what ideal should humanitarian organizations tend toward and the path to undertake in such transformation. In this perspective, this paper intends to overcome this situation by proposing a supply chain maturity model specifically addressed to the humanitarian sector. In the form of a two-dimension matrix, the table aims at: 1) Objectify one organization's position regarding its transformation journey 2) Depending on the organization, identify the specific improvement areas and suggest their sequence. An instantiation of the maturity model is also proposed through the case of the Indonesian red cross.
|
|
|
Marc Schönefeld, & Malte Schönefeld. (2020). IT-Security Awareness of Emergency Alert Apps. 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. 396–405). Blacksburg, VA (USA): Virginia Tech.
Abstract: The article presents first research-in-progress results of an initial assessment of the IT-security awareness of five exemplary German-language emergency-alert apps. Emergency-alert mobile applications became part of many modular-oriented warning systems around the globe. Warning and intended population behavior relies on trust upon the integrity of any warning institution, be it governmental or private. IT-security is crucial in order not to undermine trust. Emergency apps do not fit into the typical entertainment purpose of mobile applications, and we show that their primarily focus on keeping the user safe from harm can cause a conflict of interest about distribution of scarce technical resources on a mobile device, which may again endanger IT-Security. We therefore promote a better integration and standardization of disaster management functionality on the operating system layer.
|
|
|
Mari Olsén, Niklas Hallberg, Per-Anders Oskarsson, & Magdalena Granåsen. (2020). Exploring Capabilities that Constitute Inter-Organizational Crisis 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. 417–426). Blacksburg, VA (USA): Virginia Tech.
Abstract: Crises are infrequent, unpredictable and complex events. Managing such events requires well-prepared and well-coordinated efforts by several response organizations. Hence, a sufficient inter-organizational crisis management (ICM) capability is critical for sustainable societies. To ensure the ICM capability, approaches for enhancing and evaluating it are needed. The objective of this study was to identify and elaborate a clearly defined set of capabilities that constitutes ICM capability. The study was performed by an explorative literature study, where identified capabilities related to ICM were clustered. The cluster of capabilities was iteratively evaluated and refined. The study resulted in 14 capabilities that constitute ICM capability, which were divided into core, supportive, and enabling capabilities. The set of capabilities may provide a foundation for a framework of ICM capability with the ability to support assessment of ICM performance both in exercises and in real ICM operations, as well as in the design of ICM exercises.
|
|
|
Marion Lara Tan, Sara Harrison, Julia S. Becker, Emma E.H. Doyle, & Raj Prasanna. (2020). Research Themes on Warnings in Information Systems Crisis Management Literature. 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. 1085–1099). Blacksburg, VA (USA): Virginia Tech.
Abstract: Early Warning Systems (EWS) are crucial to mitigating and reducing disaster impacts. Furthermore, technology and information systems (IS) are key to the success of EWSs. This systematic literature review investigates the research topics and themes from the past six years of Information Systems for Crisis Response and Management (ISCRAM) conference proceedings and seeks to identify the research developments and directions for EWSs to steer a discourse to advance the research in this field. Findings from a sample size of 60 papers show that there are technical, social, and topical considerations to using and advancing technology for EWSs. While technology has advanced EWSs to new levels, it is important to consider the influence of technology in the successful operation of EWSs. The results are based on the ISCRAM proceedings literature and may be broader or have different prioritization if a wider disciplinary body of literature was explored. This will be considered in the future.
|
|
|
Matti Wiegmann, Jens Kersten, Friederike Klan, Martin Potthast, & Benno Stein. (2020). Analysis of Detection Models for Disaster-Related Tweets. 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. 872–880). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media is perceived as a rich resource for disaster management and relief efforts, but the high class imbalance between disaster-related and non-disaster-related messages challenges a reliable detection. We analyze and compare the effectiveness of three state-of-the-art machine learning models for detecting disaster-related tweets. In this regard we introduce the Disaster Tweet Corpus~2020, an extended compilation of existing resources, which comprises a total of 123,166 tweets from 46~disasters covering 9~disaster types. Our findings from a large experiments series include: detection models work equally well over a broad range of disaster types when being trained for the respective type, a domain transfer across disaster types leads to unacceptable performance drops, or, similarly, type-agnostic classification models behave more robust at a lower effectiveness level. Altogether, the average misclassification rate of~3,8\% on performance-optimized detection models indicates effective classification knowledge but comes at the price of insufficient generalizability.
|
|
|
Md Fitrat Hossain, Thomas Kissane, Priyanka Annapureddy, Wylie Frydrychowicz, Sheikh Iqbal Ahamed, Naveen Bansal, et al. (2020). Implementing Algorithmic Crisis Alerts in mHealth Systems for Veterans with PTSD. 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. 122–133). Blacksburg, VA (USA): Virginia Tech.
Abstract: This paper seeks to establish a machine learning driven method by which a military veteran with Post-Traumatic Stress Disorder (PTSD) is classified as being in a crisis situation or not, based upon a given set of criteria. Optimizing alerting decision rules is critical to ensure that veterans at highest risk for mental health crisis rapidly receive additional attention. Subject matter experts in our team (a psychologist, a medical anthropologist, and an expert veteran), defined acute crisis, early warning signs and long-term crisis from this dataset. First, we used a decision tree to find an early time point when the peer mentors (who are also veterans) need to observe the behavior of veterans to make a decision about conducting an intervention. Three different machine learning algorithms were used to predict long term crisis using acute crisis and early warning signs within the determined time point.
|
|
|
Mehdi Ben Lazreg, Usman Anjum, Vladimir Zadorozhny, & Morten Goodwin. (2020). Semantic Decay Filter for Event Detection. 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. 14–26). Blacksburg, VA (USA): Virginia Tech.
Abstract: Peaks in a time series of social media posts can be used to identify events. Using peaks in the number of posts and keyword bursts has become the go-to method for event detection from social media. However, those methods suffer from the random peaks in posts attributed to the regular daily use of social media. This paper proposes a novel approach to remedy that problem by introducing a semantic decay filter (SDF). The filter's role is to eliminate the random peaks and preserve the peak related to an event. The filter combines two relevant features, namely the number of posts and the decay in the number of similar tweets in an event-related peak. We tested the filter on three different data sets corresponding to three events: the STEM school shooting, London bridge attacks, and Virginia beach attacks. We show that, for all the events, the filter can eliminate random peaks and preserve the event-related peaks.
|
|
|
Michael Holzhüter, & Ulrich Meissen. (2020). A Decentralized Reference Architecture for Interconnected Systems in Emergency 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. 961–972). Blacksburg, VA (USA): Virginia Tech.
Abstract: Optimal communication and information exchange are key elements for handling complex crises or disaster situations. With the increasing number of heterogeneous ICT systems, also raises the importance of adequate support for interconnectivity and information logistics between stakeholders to thoroughly gather information and to make quick but precise decisions. The main purpose of the information exchange is then to manage the crisis as quickly as possible, to provide full information to protect first responders' health and safety, to optimally dispatch resources, and to ensure coordination between different relief forces. Based on an end user survey with a particular focus on first responders, this paper introduces an evolutionary architecture to enable information exchange in crises situation or disasters. The aim is to provide a decentralized approach among heterogeneous ICT-systems which abstracts from the underlying communication technologies and heterogeneity of connected systems and fulfills the functional and non-functional requirements from end users.
|
|
|
Miguel Ramirez de la Huerga, Victor A. Bañuls, Pilar Ortiz Calderon, & Rocio Ortiz Calderon. (2020). A Delphi-Based Approach for Analysing the Resilience Level of Local Goverments in a Regional Context. 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. 602–611). Blacksburg, VA (USA): Virginia Tech.
Abstract: This article shows the research process carried out by Regional Government of southern Europe, with more than 8 million citizens, to create an Information System to serve as a diagnostic and certification model for the resilience level of the municipalities of that region. This Information System will allow the local authorities of the regional governments to know in what situation they are and what they should do to improve their resilience level. The research framework is based on the best practices in urban resilience. One of the relevant characteristics of the work is the integration of the knowledge of a very heterogeneous group of experts for the identification of the special needs of the target region that has been articulated through a Delphi process.
|
|