Abstract: Microblogs are an opportunity for scavenging critical information such as sentiments. This information can be used to detect rapidly the sentiment of the crowd towards crises or disasters. It can be used as an effective tool to inform humanitarian efforts, and improve the ways in which informative messages are crafted for the crowd regarding an event. Unique characteristics of microblogs (lack of context, use of jargon etc) in Tweets expressed by a message-sharing social network during a disaster response require special handling to identify sentiment. We present a systematic evaluation of approaches to accurately and precisely identify sentiment in these Tweets. This paper describes sentiment detection expressed in 3698 Tweets, collected during the September 2010, San Bruno, California gas explosion and resulting fires. The data collected was manually coded to benchmark our techniques. We start by using a library of words with annotated sentiment, SentiWordNet 3.0, to detect the basic sentiment of each Tweet. We complemented that technique by adding a comprehensive list of emoticons, a sentiment based dictionary and a list of out-of-vocabulary words that are popular in brief, online text communications such as lol, wow, etc. Our technique performed 27% better than Bayesian Networks alone, and the combination of Bayesian networks with annotated lists provided marginal improvements in sentiment detection than various combinations of lists. © 2012 ISCRAM.

Abstract: Natural disasters such as hurricanes, floods, earthquakes, fires as well as those of manmade origins, such as dam breaches, necessitate communication between and among emergency responders, governmental officials, and the impacted populace. As the third largest country in terms of area and first in terms of population, China is no stranger to natural and manmade disasters of varying kinds. Until recently, the country had no central focus on dealing with such events and allowed local officials for the most part to plan and carry out all of the activities involved in disaster planning and management. Advances in the Chinese economy and more of a nationalist slant on policies have attempted to broaden the planning scope and management across the country with varying results. The deployment of wireless communications across China has assisted in disaster planning and management activities, but inconsistent policies and a haphazard approach to its deployment have hindered its ability to fully aid such activities. With a population of more than 1.3 billion (2010 Census) and its wide geography, China is one of the most natural disaster-affected countries in the world. Many natural disasters occur in China frequently and often result in severe damage and loss of life. In response to these events, several strategies for emergency management should be implemented, but in particular the integration of the deployment of wireless networks throughout the rural parts of the country with disaster/emergency planning for the same areas should be undertaken. © 2012 ISCRAM.

Abstract: Over the last two decades a significant number of projects tried to convey the concept of business process man-agement to the domain of emergency management. Most of these approaches sought a partial automation for the execution of standard operating procedures in the sense of workflow support, while others strived for the sup-port and integration of information management and data streams in command centres during a crisis. This pa-per focuses on the planning of disaster response for reasons of better preparedness. It discusses whether emer-gency management organisations can capitalize on off-the-shelf business process modelling tools to prepare for disasters more effectively, and whether the concepts of process modelling can be applied to standard operating procedures and vice versa. Moreover, it investigates whether such tools can efficiently support a collaborative preparation of police, fire departments, and rescue organizations. This paper will demonstrate why conventional business process means are inapplicable as planning tool in this domain. And it will also give an outlook to so called smart checklists that might be better suited both for the planning and response phase of emergency epi-sodes. © 2012 ISCRAM.

Abstract: The effectiveness of emergency response largely depends on having a precise, up-to-date situational picture. With the World Wide Web having evolved from a small read-only text collection to a large-scale collection of socially created data accessible both to machines and humans alike, with the advent of social media and ubiquitous mobile applications, new sources of information are available. Currently, that potentially valuable information remains mostly unused by the command staff, mainly because the sheer amount of information cannot be handled efficiently. In this paper, we show an approach for turning massive amounts of unstructured citizen-generated content into relevant information supporting the command staff in making better informed decisions. We leverage Linked Open Data and crowdsourcing for processing data from social media, and we show how the combination of human intelligence in the crowd and automatic approaches for enhancing the situational picture with Linked Open Data will lead to a Web 3.0 approach for more efficient information handling in crisis management. © 2012 ISCRAM.

Abstract: We report on the use of a team of trusted digital volunteers during the 2011 Shadow Lake Fire that occurred in the US Pacific Northwest to extend the social media capacity of a Type I incident management team. In this case study, we outline the tools and processes used by this virtual team to coordinate their activities, monitor social media communication and to establish communications with the public around the event. Finally, we discuss the potential merits and limitations of implementing a team of trusted volunteers and explore how this idea could be incorporated into emergency management organizations. © 2012 ISCRAM.

Abstract: Recent findings from fieldwork conducted at emergency operation centers (EOC) suggest that currently deployed emergency management information systems (EMIS) are not supporting properly the anticipation of individual actions in cooperative work. We present these findings in this paper and introduce joint action theory as an interaction approach to design technologies that explicitly provide for this kind of support. Our main arguments are: (1) contemporary EMIS are affecting negatively cooperative work at EOCs due to their lack of support for the anticipation of individual actions; (2) Available theory that emphasizes the role of anticipation on cooperative work is not impacting on the design of EMIS due to misalignments between the theory and contemporary situations; (3) Joint action theory provides an alternative framework to correct these misalignments; and (4) Joint action theory provides designers of EMIS with guides for an interaction design that supports anticipatory actions in EOCs.

Abstract: In this paper we discuss ethical challenges arising around IT supported interoperability in multi-agency emergency management and explore some methodological responses.

Abstract: Alerting the population during crisis using available communication systems can significantly reduce the impact of emergency situations. However, the understanding of the alert and trust by recipients is influenced by the alert message content and style. It is therefore desirable that alert messages are formulated with sufficient information and in a style that eases understanding of the message and fosters trust, so that the recommended protective actions are actually undertaken. Within the EU Alert4All project, an alert message dispatcher is being currently implemented, which disseminates alert messages through multiple communication systems in a harmonized manner, fostering best practices in the formulation of alert messages in a user-friendly manner. The design of the dispatcher features and graphical user interface was supported by a field practitioner workshop with participants from different European countries. This paper describes the workshop methodology, its results and the impact on the message dispatcher design.

Abstract: This paper examines the problem of achieving efficient inter-organizational collaboration during emergency response. The authors interviewed 11 representatives from Norwegian emergency agencies and supporting organizations about a hypothetical scenario involving a large-scale chemical incident. The interviews resulted in the identification and categorization of more than 45 actors that would be involved in the response effort, clarification of the individual capabilities and knowledge those actors would possess, and descriptions of how they would interact and communicate with each other. The results illustrate the complexity and necessity of achieving inter-organizational collaboration by showing how capabilities and knowledge are distributed and communicated across different actors, and suggest that such communications are mainly verbal. Based on this, the paper discusses challenges and opportunities for improving inter-organizational collaboration in the future.

Abstract: This research project investigated the incident response mechanism used by the chemical industry for handling extremely hazardous chemicals. The mechanism was described as the policies, procedures, practices, tools, and methods used to conduct incident response. The results from the study determined what technologies, specifically software and information systems, could be utilized to improve the chemical facility incident response mechanism. The chemical industry is responsible for process safety management at all of its facilities, especially those that have off-site consequences in the event of an unplanned release. The processes and procedures of local, regional and national emergency responders have been studied thoroughly. An area of research that is lacking is the study of incident response policies and procedures within the boundaries of a chemical site. Results of the analysis determined that the chemical industry, in general, does not take advantage of available information technology when responding to unplanned releases.

Abstract: It has long been recognized that the management of emergencies requires that response organisations act flexibly, becoming an “emergent organisation” to better manage the fact that disasters do not follow scripts. Nevertheless, recent research shows that crisis response organisations prefer to follow patterns adequate for normal situations. Arguably, the resistance to become an emergent organisation could be related to poor understanding of how to move from disorganisation to self-organisation. We extend a recent system dynamics work by Tu, Wang and Tseng, describing the transition from disorganisation to self-organisation in the Palau case, to analyse the management of disorganisation in the fatal Hatlestad landslide in Norway. We suggest that the causal structure of the system dynamics model describing the Palau and the Hatlestad case should be considered a candidate for an emergent “middle-range theory” describing the management of disorganisation in emergencies. We propose specific data collection to test the candidate theory.

Abstract: Successful decision making and task execution in emergency management require appropriate levels of situation awareness (SA). This paper proposes an ontology-based model for the design of a computer-based system, Situation Aware Vigilant Emergency Reasoner (SAVER) that supports the individual, shared and team SA of managers in emergency situations. SAVER is evaluated in simulated experiments that demonstrate the improvements in SA performance. The paper provides a complete description of the SAVER design, implementation, evaluation and its proposed extension from a proof-of-concept to a production environment.

Abstract: Spatial partitioning consists of the problem of finding the best segmentation of an area under specific conditions. The final goal is to identify parts of the area where a number of resources could be allocated. Such cases are common in disaster management scenarios. In this paper, we consider such a scenario and propose a methodology for the resource allocation for emergency response. We utilize an intelligent technique that is based on the Particle Swarm Optimization algorithm. We define the problem by giving specific formulations and describe the proposed algorithm. Moreover, we provide a method for separating the area into cells and describe a technique for calculating cell weights based on the underlying spatial data. Finally, we present a case study for allocating a number of ambulances and give numerical results concerning the run time and the total coverage of the examined area.