|
Ulrich Meissen, & Frank Fuchs-Kittowski. (2014). Towards a reference architecture of crowdsourcing integration in early warning systems. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 334–338). University Park, PA: The Pennsylvania State University.
Abstract: Crowdsourcing has the potential to become a crucial information source in disaster management. In order to become effective as an integrated part of disaster management systems it is important to set the general architectural foundations for such integrations beyond prototypical experiments. This paper discusses general architectural principles of the application of crowdsourcing in Early Warning Systems (EWS). An integrated architecture is proposed to use classical sensor data and crowdsourcing in an EWS solution. Therefore, typical components of crowdsourcing applications are identified and mapped to monitoring subsystems of EWS's. Three main structural variants of applying crowdsourcing in early warning systems along the example of a prototypical extension of two existing large-scale hydro-meteorological warning systems are presented.
|
|
|
Ulrich Meissen, Markus Hardt, & Agnès Voisard. (2014). Towards a general system design for community-centered crisis and emergency warning systems. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 155–159). University Park, PA: The Pennsylvania State University.
Abstract: Early Warning Systems (EWS) provide an effective measure for better disaster preparedness, response, and mitigation. The effectiveness of EWS depends highly on the ability to distribute alert message to the persons that will be affected. In this context mobile devices play already a vital role in the ability to reach people in time and at the endangered location. Most existing approaches focus on mass dissemination methods via SMS and Cell-Broadcasting. As these approaches are effective to inform masses about a disaster with one message for all they have their weaknesses in telling the people how to respond according to their location and provide individual guidance (e.g. by maps) within specific communities. Research in disaster management gives strong evidence that the later is often crucial for better disaster response. Accordingly, we witness an increasing demand for more community-centered warnings systems solutions. This paper introduces the general foundations and architecture for alert services on mobile devices that adapt incoming alert information to the profile and situation of user groups and even individual users. The approach is scalable for different communitycentered warning systems. Its first applicability and community engagement effects are shown in the example of the community-centered public disaster alert system in Germany and a target group specific weather hazard alert system, KATWARN and WIND with currently over 2.5 million subscribed users, which was developed by the authors.
|
|
|
Torbjørg Træland Meum. (2014). An action design research approach to developing emergency management systems. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 175–179). University Park, PA: The Pennsylvania State University.
Abstract: We propose Action Design Research (ADR) as an approach to promote user participation and mutual learning in the design and development of systems for emergency management based on social media technologies. We outline some design challenges related to the dynamic and evolving nature of social media, and emphasize an iterative design process that is strongly oriented toward collaboration and change involving both the researcher and the user community. In particular, we emphasize the transformative power of social media and argue for design approaches that take into account the new dimension of e-participation throughout the design process.
|
|
|
Stella Moehrle. (2014). On the assessment of disaster management strategies. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 215–219). University Park, PA: The Pennsylvania State University.
Abstract: Decision support systems can recommend strategies for disaster management, which can be further discussed by decision-makers. To provide rationales for the recommendations, the strategies need to be assessed according to relevant criteria. If several strategies are available, the criteria can be used for ranking the strategies. This paper addresses the issue concerning the choice of suitable criteria from several perspectives. The assessment integrates concepts on robustness, experience with regard to the implementation of a strategy, quantifiable ratios which can be deduced from simulations, and system-specific parameters. Objectives are to facilitate transparency with respect to the assessments, to provide a basis for discussions concerning the strategies, and to preserve adaptability and flexibility to account for the variability of disasters and users' preferences. The assessment should be used for ranking solutions gained from a case-based reasoning system and to reveal contributions of criteria values to the overall assessment.
|
|
|
Kayvan Yousefi Mojir, & Sofie Pilemalm. (2014). Emerging communities of collaboration: Co-location in emergency response systems in the 'Safety house' in Sweden. 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. 546–555). University Park, PA: The Pennsylvania State University.
Abstract: Co-location as a form of network governance is a way of organizing response teams when responding to an emergency situation. At the 'Safety house' in the province of Jämtland in Sweden main emergency response actors and supporting actors work together in a shared physical place in order to facilitate the process of cooperation and joint decision making. In order to identify the strengths, weaknesses, obstacles, needs and information system role, we explored this case by looking at how the involved actors experience this new working context. We applied an analytical framework developed specifically for new forms of emergency response. It was found that co-location of actors increases the efficiency in using professional response resources and shortens the emergency response time. Information systems can have a significant role in improving the collaboration between actors at the 'Safety house'. However secrecy issues, the problem of control and politics and the evaluation of the performance of actors are major challenges which face further development of the co-location concept.
|
|
|
Thomas Münzberg, Marcus Wiens, & Frank Schultmann. (2014). A strategy evaluation framework based on dynamic vulnerability assessments. 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. 45–54). University Park, PA: The Pennsylvania State University.
Abstract: Assessing a system's vulnerability is a widely used method to estimate the effects of risks. In the past years, increasingly dynamic vulnerability assessments were developed to display changes in vulnerability over time (e.g. in climate change, coastal vulnerability, and flood management). This implies that the dynamic influences of management strategies on vulnerability need to be considered in the selection and implementation of strategies. For this purpose, we present a strategy evaluation framework which is based on dynamic vulnerability assessments. The key contribution reported in this paper is an evaluation framework that considers how well strategies achieve a predefined target level of protection over time. Protection Target Levels are predefined objectives. The framework proposed is inspired by Goal Programming methods and allows distinguishing the relevance of time-dependent achievements by weights. This enables decision-makers to evaluate the overall performance of strategies, to test strategies, and to compare the outcome of strategies.
|
|
|
Aibek Musaev, De Wang, & Calton Pu. (2014). LITMUS: Landslide detection by integrating multiple sources. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 677–686). University Park, PA: The Pennsylvania State University.
Abstract: Disasters often lead to other kinds of disasters, forming multi-hazards such as landslides, which may be caused by earthquakes, rainfalls, water erosion, among other reasons. Effective detection and management of multihazards cannot rely only on one information source. In this paper, we evaluate a landslide detection system LITMUS, which combines multiple physical sensors and social media to handle the inherent varied origins and composition of multi-hazards. LITMUS integrates near real-time data from USGS seismic network, NASA TRMM rainfall network, Twitter, YouTube, and Instagram. The landslide detection process consists of several stages of social media filtering and integration with physical sensor data, with a final ranking of relevance by integrated signal strength. Applying LITMUS to data collected in October 2013, we analyzed and filtered 34.5k tweets, 2.5k video descriptions and 1.6k image captions containing landslide keywords followed by integration with physical sources based on a Bayesian model strategy. It resulted in detection of all 11 landslides reported by USGS and 31 more landslides unreported by USGS. An illustrative example is provided to demonstrate how LITMUS' functionality can be used to determine landslides related to the recent Typhoon Haiyan.
|
|
|
Dick Ooms, & Willem-Jan Van Den Heuvel. (2014). If every nail looks different, you need different hammers: Modeling civil-military interaction. 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. 349–353). University Park, PA: The Pennsylvania State University.
Abstract: In the response to emergencies and disasters, effective cooperation and information exchange between military and civil actors is essential. However, in practice, the quality of civil-military interaction (CMI) leaves much to be desired. Our research takes an engineering approach, which is complementary to most behavioral-oriented research in the CMI domain. In particular, we seek to support CMI processes with innovative Information Technology solutions. To this end, we are developing a comprehensive conceptual model of the CMI domain, which is currently lacking. This paper contributes to its development by investigating candidate technologies and defining CMI domain model requirements. Exploiting these requirements as criteria, we have evaluated three modeling methods and languages, i.e. the Unified Modeling Language (UML), the Business Process Modeling Notation (BPMN) and the Design and Engineering Methodology for Organizations (DEMO). Based on the comparative study, we conclude that a combination of these is required for modeling the CMI domain.
|
|
|
Christopher E. Oxendine, Emily Schnebele, Guido Cervone, & Nigel Waters. (2014). Fusing non-authoritative data to improve situational awareness in emergencies. 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. 762–766). University Park, PA: The Pennsylvania State University.
Abstract: In order to coordinate emergency operations and evacuations, it is vital to accurately assess damage to people, property, and the environment. For decades remote sensing has been used to observe the Earth from air, space and ground based sensors. These sensors collect massive amounts of dynamic and geographically distributed spatiotemporal data every day. However, despite the immense quantity of data available, gaps are often present due to the specific limitations of the sensors or their carrier platforms. This article illustrates how nonauthoritative data such as social media, news, tweets, and mobile phone data can be used to fill in these gaps. Two case studies are presented which employ non-authoritative data to fill in the gaps for improved situational awareness during damage assessments and emergency evacuations.
|
|
|
Marius J. Paulikas, Andrew Curtis, & Thomas Veldman. (2014). Spatial video street-scale damage assessment of the Washington, Illinois Tornado of 2013. 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. 329–333). University Park, PA: The Pennsylvania State University.
Abstract: This paper advances a growing body of mobile mapping work which captures building scale tornado damage in order to reveal vulnerabilities, or protections, within an otherwise apparently homogenous damage path. The hope is to find how micro geography, or built environment structure patterning might lead to policy advances with regards to rebuilding of critical infrastructure in tornado prone areas. This paper will use spatially encoded video to record damage patterns for the Washington, Illinois tornado of November 17, 2013. What makes this event notable is the location and time of year which can be considered outside the norm. Individual building damage data are coded using the Tornado Injury Scale (TIS) and then analyzed using two forms of local area spatial analysis – a Getis-Ord (Gi) z-score analysis to identify hotspots of damage, and a Local Moran's I to identify building outliers within hotspots.
|
|
|
Jens Pottebaum, Robin Marterer, & Steffen Schneider. (2014). Taxonomy of IT support for training emergency response & management. 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. 374–378). University Park, PA: The Pennsylvania State University.
Abstract: Training is a prerequisite for effective and efficient emergency response and management. Information technology (IT) offers high potential to support various educational methods and environments. One example for interdependent use cases is given by planning, controlling, observation and debriefing of training exercises. Dedicated IT systems are available to support these use cases; nevertheless, there is no joint understanding of system use cases, types and functionality as a fundament for scientific and technological progress. This work in progress paper presents results of literature and market research complemented by expert interviews leading to a taxonomy of relevant IT components and systems.
|
|
|
Hemant Purohit, Shreyansh Bhatt, Andrew Hampton, Valerie Shalin, Amit Sheth, & John Flach. (2014). With whom to coordinate, why and how in ad-hoc social media communities during crisis response. 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. 787–791). University Park, PA: The Pennsylvania State University.
Abstract: During crises directly affected people and observers join social media communities to discuss the event. They may share information relevant to response coordination, for example, specific resource needs. However, responders face a massive data overload and lack the time to monitor social media traffic for important and trustworthy information. To address these challenges, response teams may attempt manual filtering methods, resulting in limited coverage and quality. Hence, we propose a computational framework for extracting specific resource-related information, and an interface for identifying and engaging with influential participants in the dynamic, evolving social media community. Our approach helps to identify those virtual responders who serve both as sources and disseminators of important information to assist in coordinated emergency response.
|
|
|
Jaziar Radianti, Julie Dugdale, Jose J. Gonzalez, & Ole-Christoffer Granmo. (2014). Smartphone sensing platform for emergency management. 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. 379–383). University Park, PA: The Pennsylvania State University.
Abstract: The increasingly sophisticated sensors supported by modern smartphones open up novel research opportunities, such as mobile phone sensing. One of the most challenging of these research areas is context-aware and activity recognition. The Smart Rescue project takes advantage of smartphone sensing, processing and communication capabilities to monitor hazards and track people in a disaster. The goal is to help crisis managers and members of the public in early hazard detection, prediction, and in devising risk-minimizing evacuation plans when disaster strikes. In this paper we suggest a novel smartphone-based communication framework. It uses specific machine learning techniques that intelligently process sensor readings into useful information for the crisis responders. Core to the framework is a content-based publish-subscribe mechanism that allows flexible sharing of sensor data and computation results. We also evaluate a preliminary implementation of the platform, involving a smartphone app that reads and shares mobile phone sensor data for activity recognition.
|
|
|
Murali Raman, Magiswary Dorasamy, Saravanan Muthaiyah, & Maniam Kaliannan. (2014). Web-based community disaster management and awareness system (CEMAS) in Malaysia. 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. 384–393). University Park, PA: The Pennsylvania State University.
Abstract: Emergency situations are unavoidable. This paper presents the functions inherent in a prototype system that was developed in Malaysia for emergency management. The prototype is potentially useful in Selangor, a state in Malaysia that is prone to natural disasters such as flash floods and landslides. The paper is presented as a report of our on-going project in Malaysia and the intended future work regarding web-based emergency management systems in Malaysia. This prototype development is funded by the Ministry of Education in Malaysia and supported by the National Security Council of Malaysia (Majilis Keselamatan Negara, MKN).
|
|
|
Caroline Rizza, & Ângela Guimarães Pereira. (2014). Building a resilient community through social network: Ethical considerations about the 2011 Genoa floods. 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. 289–293). University Park, PA: The Pennsylvania State University.
Abstract: This paper considers the role of social media in the response to the flooding of 2011 in Genoa (Italy), caused by flash floods during torrential rainfall. Volunteer students created a Facebook page to communicate with citizens and organize support and rescue activities. In this paper, we first look at the story of the 2011 Genoa floods from the point of view of the news media to gain insights into the imaginaries behind the use of social media in situations of natural disaster. Second, we look at a communication partnership between citizenry and public authorities for its value in building resilience to disaster among communities. Ethical and social dimensions of these partnerships are analysed.
|
|
|
Marco Romano, Teresa Onorati, Paloma Díaz, & Ignacio Aedo. (2014). Improving emergency response: Citizens performing actions. 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. 170–174). University Park, PA: The Pennsylvania State University.
Abstract: The role of common citizens within the emergency management (EM) process is crucial in order to support efficiently the operators' activities during the response phase. Moreover, their participation is strictly related to their profile and their experience in previous events. In a previous contribution we identified the different roles that the citizens can play for an effective cooperation with the EM workers. In this paper, we introduce an emergency tool based on a mobile application designed to support the activities of the citizens acting as Agent. The Agents have specific capabilities recognized by the EM Operation Center (OC) to execute actions under the remote supervision of the EM operators. The proposed tool allows the Agents to receive information from the OC and to visualize it through an advanced visualization modality. In particular, available information is previously collected by the center from the witnesses and the affected people that have alerted about it.
|
|
|
Angel Ruiz-Zafra, Ana-Gabriela Núñez, Carmen Penadés, José H. Canós-Cerdá, & Marcos R. S. Borges. (2014). SUCRE: Supporting users, controllers and responders in emergencies. 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. 255–259). University Park, PA: The Pennsylvania State University.
Abstract: We use the term “Personal Safety Assistants” (PSAs) to refer to a family of mobile information systems that intend to reduce the risks of both citizens and responders in emergency responses. Using their mobile devices, they can access to personalized views of the emergency plans including context-aware evacuation instructions or real time guidance to specific locations for rescue operations, among others. Additionally, both responders and citizens act as context sources sending fresh information (e.g. pictures of damaged areas) to the command and control center, increasing situational awareness. In this paper, we show how the SUCRE infrastructure collects and processes contextual information to improve the information infrastructure during responses. We describe the current status of the system and outline the incoming enhancements.
|
|
|
Johannes Sautter, Janina Hofer, Sven Wirth, Wolf Engelbach, Matthias Max, Tanel Tenso, et al. (2014). Local-specific resource planning for mass casualty incidents. 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. 503–507). University Park, PA: The Pennsylvania State University.
Abstract: In the situation of mass casualty incidents in Germany the questions that always remain are what and how much resources are needed to provide the best response. Furthermore, there are many local-specific constraints that exist, such as the density of hospitals nearby, what their surgery capacities are like, the distance between the local rescue bases and the incident scene as well as the level of preparedness of first responders. This paper describes an organisational approach to elaborate the specific tactical strategies that take part in preparedness planning. Furthermore, this paper will give insight and explore a simulation information system to support local medical response managers in elaborating those strategies in an office environment.
|
|
|
Frank Schätter, Sascha Meng, Marcus Wiens, & Frank Schultmann. (2014). A multi-stage scenario construction approach for critical infrastructure protection. 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. 399–408). University Park, PA: The Pennsylvania State University.
Abstract: Protecting critical infrastructures (CIs) against external and internal risks in an increasingly uncertain environment is a major challenge. In this paper we present a generic multi-stage scenario construction approach that is applicable to a wide range of decision problems in the field of CI protection. Our approach combines scenario construction and decision support, whereby we explicitly consider the performance of decision options which have been determined for a set of initial scenarios. Because of the iterative character of our approach, consequences of decision options and information updates are evolutionary processed towards advanced scenarios. By disturbing vulnerable or critical parts of CIs, cascading effects between interrelated CIs and the responses to the decision options can be determined. We apply this scenario-construction technique to two civil security research projects. One focuses on protecting food supply chains against disruptions, whereas the other aims at securing public railway transport against terrorist attacks.
|
|
|
Svend-Jonas Schelhorn, Benjamin Herfort, Richard Leiner, Alexander Zipf, & João Porto De Albuquerque. (2014). Identifying elements at risk from OpenStreetMap: The case of flooding. 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. 508–512). University Park, PA: The Pennsylvania State University.
Abstract: The identification of elements at risk is an essential part in hazard risk assessment. Especially for recurring natural hazards like floods, an updated database with information about elements exposed to such hazards is fundamental to support crisis preparedness and response activities. However, acquiring and maintaining an up-to-date database with elements at risk requires both detailed local and hazard-specific knowledge, being often a challenge for local communities and risk management bodies. We present a new approach for leveraging Volunteered Geographic Information to identify elements at risk from the free and open-source mapping project OpenStreetMap. We present initial results from a case study in the city of Cologne, Germany, to validate our approach in the case of flood-hazard. Our results show that the identification of elements at flood risk from OpenStreetMap is a suitable and cost-effective alternative for supporting local governments and communities in risk assessment and emergency planning.
|
|
|
Krispijn Scholte, & Leon J.M. Rothkrantz. (2014). Personal warning system for vessels under bad weather conditions. 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. 359–368). University Park, PA: The Pennsylvania State University.
Abstract: Many services provide weather forecasts, including severe weather alerts for the marine. It proves that many ships neglect the warnings because they expect to be able to handle the bad weather conditions. In order to identify possible unsafe situations the Coast Guard needs to observe marine vessel traffic 24 hours, 7 days a week. In this paper we propose a system that is able to support the Coast Guard. Ships can be localized and tracked individually using the Automatic Identification System (AIS). We present a system which is able to send a personal alert to ships expected to be in danger now or the near future. Ships will be monitored in the dangerous hours and routed to safe areas in the shortest time. The system is based on AIS data, probabilistic reasoning and expertise from the Coast Guard. A first prototype will be presented for open waters around the Netherlands.
|
|
|
Zhou Sen, & Bartel A. Van De Walle. (2014). How intellectual capital reduces stress on organizational decision-making performance: The mediating roles of task complexity and time pressure. 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. 220–224). University Park, PA: The Pennsylvania State University.
Abstract: Previous research claimed that organizational stress, due to task complexity and time pressure, leads to considerably negative effects on the decision-making performance of individuals and organizations. At the same time, intellectual capital (IC), in providing intangible internal and external organizational assets has a positive effect on organizational decision-making performance. This paper develops a structural equation model to analyze the relationships among IC, task complexity, time pressure and decision-making performance. Empirical data are collected from 374 participants, who are from universities, institutes, enterprises, government, with different occupations and expertise. We present two conclusions. First, IC consisting of internal capital, human capital and external capital leads to a reduced complexity of tasks and reduced time pressure and hence reduced organizational stress. Second, reduced organizational stress results in higher levels of performance for organizational decision-making.
|
|
|
Yongzhong Sha, Jinsong Yan, & Guoray Cai. (2014). Detecting public sentiment over PM2.5 pollution hazards through analysis of Chinese microblog. 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. 722–726). University Park, PA: The Pennsylvania State University.
Abstract: Decision-making in crisis management can benefit from routine monitoring of the (social) media to discover the mass opinion on highly sensitive crisis events. We present an experiment that analyzes Chinese microblog data (extracted from Weibo.cn) to measure sentiment strength and its change in relation to the recent PM 2.5 air pollution events. The data were analyzed using SentiStrength algorithm together with a special sentiment words dictionary tailored and refined for Chinese language. The results of time series analysis on detected sentiment strength showed that less than one percent of the posts are strong-positive or strong negative. Weekly sentiment strength measures show symmetric changes in positive and negative strength, but overall trend moved towards more positive opinions. Special attention was given to sharp bursts of sentiment strength that coincide temporally with the occurrence of extreme social events. These findings suggest that sentiment strength analysis may generate useful alert and awareness of pending extreme social events.
|
|
|
Gayane Shalunts, Gerhard Backfried, & Prinz Prinz. (2014). Sentiment analysis of German social media data for natural disasters. 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. 752–756). University Park, PA: The Pennsylvania State University.
Abstract: Analysis of social media and traditional media provides significant information to first responders in times of natural disasters. Sentiment analysis, particularly of social media originating from the affected population, forms an integral part of multifaceted media analysis. The current paper extends an existing methodology to the domain of natural disasters, broadens the support of multiple languages and introduces a new manner of classification. The performance of the approach is evaluated on a recently collected dataset manually annotated by three human annotators as a reference. The experiments show a high agreement rate between the approach taken and the annotators. Furthermore, the paper presents the initial application of the resulting technology and models to sentiment analysis of social media data in German, covering data collected during the Central European floods of 2013.
|
|
|
Yixing Shan, Lili Yang, & Roy Kalawsky. (2014). Exploring the prescriptive modeling of fire situation assessment. 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. 60–64). University Park, PA: The Pennsylvania State University.
Abstract: One of the key assumptions in Endsley's three-level Situation Awareness (SA) model is the critical role of mental models in the development and maintenance of SA. We explored a prescriptive way of modeling this essential mental process of the fire incident commanders' fire ground assessment. The modeling was drawn from the Fast and Frugal Heuristics (FFHs) program, given the strong parallels between its contentions on ecological rationality and the environment demanding of the emergency response context. This paper addresses a number of issues being encountered in the attempt of our empirical investigation.
|
|