Abstract: Experiments in crisis management are expensive and difficult to realize. There is also a lack of training facilities in real crisis environments. Serious games and simulation can provide an alternative. We developed a system which enables interactive simulation for crisis management. It is called IMACSIM (Interactive Multi Agent Crisis Simulator Interpreter and Monitor). It is composed of the following components: First a software based platform for dynamic simulating of disasters. Next an event generator which can generate different crises situations. We designed a communication infrastructure that allows agents participants in the simulation to exchange messages. Every agent is able to observe the results of crisis events, process these events and initiate appropriate actions via a waypoint system. The decision making process is distributed among autonomous agents. Some actions may have an impact on the event generator, so there is an interaction between agents and event generator. We developed a first prototype. The design and test results will be described in this paper.

Abstract: We present the first release of EMTerms (Emergency Management Terms), the largest crisis-related terminological resource to date, containing over 7,000 terms used in Twitter to describe various crises. This resource can be used by practitioners to search for relevant messages in Twitter during crises, and by computer scientists to develop new automatic methods for crises in Twitter.
The terms have been collected from a seed set of terms manually annotated by a linguist and an emergency manager from tweets broadcast during 4 crisis events. A Conditional Random Fields (CRF) method was then applied to tweets from 35 crisis events, in order to expand the set of terms while overcoming the difficulty of getting more emergency managers? annotations.
The terms are classified into 23 information-specific categories, by using a combination of expert annotations and crowdsourcing. This article presents the detailed terminology extraction methodology, as well as final results.

Abstract: This paper aims at measuring transfer learning performances across different types of crises related to sudden or unexpected events (like earthquakes, terror attacks, explosions, technological incidents) that cannot be foreseen by emergency services and on the occurrence of which they have virtually no control. Although sudden crises are present in most existing crisis datasets, as far as we are aware, no one studied their impact on classifiers performances when evaluated in an out-of-type scenario in which models are tested on a particular type of crisis unseen during training. Our contribution is threefold: (1) A new dataset of about 3,800 French tweets related to four sudden events that occurred in France annotated for both relatedness (i.e., useful vs. not useful for emergency responders) and urgency (i.e., not useful vs. urgent vs. not urgent), (2) A set of monotask and multitask zero-shot learning experiments to transfer knowledge across events and types, and finally, (3) Experiments involving few-shot learning to measure the amount of sudden events instances needed during training to guarantee good performances. When compared to a cross-event setting, our preliminary results are encouraging and show that transfer from predictable ecological crisis to sudden events is feasible and constitutes a first step towards real-time crisis management systems from social media content.

Abstract: With the current international crises such as the Ukrainian war, the ongoing climate change, or the interruptions in international supply chains and recent incidents like the earthquake in Turkey or the Ohio train derailment, it becomes more obvious that “just” protecting the society’s critical services and infrastructures will not be sufficient enough in the future. Services and infrastructures need to become more resilient to the effects of intentional threats as well as disasters caused by natural hazards to keep essential services operational and protect the people’s wellbeing. Accordingly, the solutions for achieving that and making society more resilient need to look further, beyond the boundaries of one infrastructure and beyond purely technical aspects. In this way, evolving towards a resilient society is a multi-dimensional problem integrating different viewpoints. In the technology-driven world we are living today, the social relations and interactions among individuals have become more important than ever and organizational structures influence the success or failure of technological solutions. Furthermore, many frameworks for societal/social/community resilience include as a metric the availability of essential services/critical infrastructure. Therefore, today’s technical solutions for protecting Critical Infrastructures need to play together with novel organizational, communal, and individual concepts as well as fulfill requirements from the economic, environmental, ethical and societal domains. In this panel, we will look at the impacts Critical Infrastructures are facing due to current crisis situations in different parts of the world and the effects this has on society. We will discuss among the panelists and with the audience on how existing and future concepts, methodologies and tools could help to improve resilience from a technical, organizational, and societal perspective.

Abstract: We propose an OWL/SWRL enabled ontological environment which can play a role in reporting and decision making in Humanitarian Crises (HC). We use (5WH): WHO, WHAT, WHERE, WHEN, WHY and HOW, as the main vehicle for gathering information for decision making. We implement the semantics of (5WH) through OWL models and perform reasoning with SWRL rules, in order to support decision making and create more efficient Humanitarian Response (HR). Our case study shows the feasibility of the proposal and its outcome. © 2012 ISCRAM.