Stella Moehrle. (2012). Generic self-learning decision support system for large-scale disasters. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Large-scale disasters, particularly failures of critical infrastructures, are exceptional situations which cannot be solved with standard countermeasures. The crises are complex and the decision makers face acute time pressure to respond to the disaster. IT based decision support systems provide potential solutions and assist the decision making process. Many decision support systems in emergency response and management concentrate on one kind of disaster. Moreover, complex structures are modeled and recommendations are made rule-based. This work in progress paper describes the first steps towards the development of a generic and self-learning decision support system. The methodology used is case-based reasoning. The paper concludes with a sample emergency decision process. © 2012 ISCRAM.
|
Stella Moehrle. (2013). Modeling of countermeasures for large-scale disasters using high-level petri nets. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 284–289). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: In order to support decision-making in large-scale disasters, IT-based decision support systems provide appropriate countermeasures to respond to the event. For the implementation of measures, logical and temporal dependencies have to be considered. Furthermore, factors influencing the choice of measures should be taken into account. This paper presents a generic approach to modeling sequences of countermeasures using Highlevel Petri Nets including information about the influencing factors and endangered objects. Moreover, an approach to combining several nets is proposed, which establish new sequences for recommendation. The research is part of the development of a generic decision support system for large-scale disasters. Consequently, the focus is on modeling in a generic manner and on automatic processing.
|
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.
|
Muhammad Imran, Firoj Alam, Umair Qazi, Steve Peterson, & Ferda Ofli. (2020). Rapid Damage Assessment Using Social Media Images by Combining Human and Machine Intelligence. 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. 761–773). Blacksburg, VA (USA): Virginia Tech.
Abstract: Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ~280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ~29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
|
Niels Netten, & Maarten Van Someren. (2006). Automated support for dynamic information distribution in incident management. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 230–237). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: For all emergency response personnel involved in crisis situations it is essential to timely acquire all information critical to their task performance. However, in practice errors occur in the distribution of information between these collaborating actors leading to mistakes and subsequently more damage to the situation. In this paper we present a prototype system for dynamic information distribution able to support the information flow between collaborating crisis actors. The system has been evaluated by means of simulated experiments that use data from a real incident scenario. The results indicate that automated support by means of Machine Learning method works well. Especially, when actor work context features are included, then the performance on selecting and distributing relevant information is high. Furthermore, actors acquire relevant information much faster making group communication much more efficient.
|
Gisli Olafsson. (2012). Humanitarian response in the age of mass collaboration and networked intelligence. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: The current humanitarian system is based on institutions created during the Industrial Age. It was built when connectivity was a very scarce resource and information sharing was something that only happened during meetings. The increased resiliency of mobile communication networks and the proliferation of satellite based network connectivity have lead to information being much easier to share. At the same time the rise of social networks and the explosive growth of mobile ownership amongst the affected communities has lead to a new way of communicating. Furthermore the large institutional humanitarian response organizations are no longer the only responders, with multiple smaller organizations responding. This paper looks at the opportunities new technologies have provided in rethinking the humanitarian response system and how new approaches may address some of the key issues faced in large-scale disasters in recent years. © 2012 ISCRAM.
|
Babajide Osatuyi, & Michael J. Chumer. (2010). An empirical investigation of alert notifications: A temporal analysis approach. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: As the deployment of situational awareness mechanisms such as geothermal sensors, use of social network sites, and information and communication technologies (e.g., cell phones) become increasingly widespread to emergency responders, the problem of alert analysis has become very important. Broadcast of large amounts of alerts sent back to command centers for processing may impair the ability of analysts to connect dots that may otherwise adequately enable them to make informed decisions in a timely fashion. This paper investigates trends and patterns embedded in alert notifications generated over a given period of time in order to uncover correlations that may exist in the data. Data for this study are obtained from the National Center for Crisis and Continuity Coordination (NC4). We employ classical time series analysis to understand, explain and predict trends and patterns in the data. This work presents results obtained thus far in the quest for the effect of passage of time on alert patterns. Implications of this work in practice and research are discussed.
|
Oduor Erick Nelson Otieno, Anna Gryszkiewicz, Nihal Siriwardanegea, & Fang Chen. (2010). Concept for intelligent integrated system for crisis management. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In this document, we describe the need for providing a uniform common picture that is missing in several crisis management decision support tools. Through research, we have reviewed some existing crisis management support systems in use and noted key user requirements that these tools are missing. A significant point of this research is to stress the importance of developing a decision support system that would improve the way an ideal support system would collect, analyze and disseminate necessary information to a crisis management decision maker. We also note the importance of ensuring that such a tool presents information to its user over a user friendly interface. The structure thus developed should be a standalone application that could be incorporated into existing platforms (Rinkineva, 2004) such as cell phones, PDAs and laptops.
|
Peng Xia, Ji Ruan, Dave Parry, Jian Yu, & Sally Britnell. (2023). Enhancing Triage Training for Mass Casualty Incidents with Virtual Reality and Artificial Intelligence. In V. L. Thomas J. Huggins (Ed.), Proceedings of the ISCRAM Asia Pacific Conference 2022 (pp. 68–76). Palmerston North, New Zealand: Massey Unversity.
Abstract: Mass casualty incidents (MCIs) occur with natural or man-made disasters. Training emergency staff for combating MCIs is essential, but the cost can be high as such incidents rarely occur, and a physical simulation is resource-intensive. Triage is a critical task in dealing with MCIs. In this paper, we propose to use Virtual Reality (VR) and Artificial Intelligence (AI) technologies to build a low-cost, high-efficient system for MCI triage training. Our system captures more comprehensive training data and utilizes state-of-the-art AI evaluation methods.
|
Stephen Potter, & Gerhard Wickler. (2008). Model-based query systems for emergency response. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 495–503). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In this paper we describe the approach adopted and experiences gained during a project to develop a general architecture that aims to harness advanced sensor, modelling and Grid technologies to assist emergency responders in tackling emergencies (specifically fire emergencies). Here we focus on the command and control aspects of this architecture, and in particular, on a query-based approach that has been adopted to allow end users to interact with available models of physical and other phenomena. The development of this has provided a number of insights about the use of such models, which along with the approach itself, should be of interest to any considering similar applications.
|
Stephen Potter, Yannis Kalfoglou, Harith Alani, Michelle Bachler, Simon Buckingham Shum, Rodrigo Carvalho, et al. (2007). The application of advanced knowledge technologies for emergency response. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 361–368). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Making sense of the current state of an emergency and of the response to it is vital if appropriate decisions are to be made. This task involves the acquisition, interpretation and management of information. In this paper we present an integrated system that applies recent ideas and technologies from the fields of Artificial Intelligence and semantic web research to support sense-and decision-making at the tactical response level, and demonstrate it with reference to a hypothetical large-scale emergency scenario. We offer no end-user evaluation of this system; rather, we intend that it should serve as a visionary demonstration of the potential of these technologies for emergency response.
|
Wolfgang Raskob, Florian Gering, & Valentin Bertsch. (2009). Approaches to visualisation of uncertainties to decision makers in an operational decision support system. In S. J. J. Landgren (Ed.), ISCRAM 2009 – 6th International Conference on Information Systems for Crisis Response and Management: Boundary Spanning Initiatives and New Perspectives. Gothenburg: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Decision making in case of any emergency is associated with uncertainty of input data, model data and changing preferences in the decision making process. Uncertainty handling was from the beginning an integral part of the decision support system RODOS for the off-site emergency management following nuclear or radiological emergencies. What is missing so far is the visualisation of the uncertainties in the results of the model calculations. In this paper we present the first attempt to visualise uncertain information in the early and late phase of the decision making process. For the early phase, the area of sheltering was selected as example. For the later phase, the results of the evaluation subsystem of RODOS were selected being used for the analysis of remediation measures such as agricultural management options. Both attempts are still under discussion but the presentation of the early phase uncertainty will be realised in the next version.
|
Wolfgang Raskob, Valentin Bertsch, Jutta Geldermann., Sandra Baig, & Florian Gering. (2005). Demands to and experience with the decision support system rodos for off-site emergency management in the decision making process in Germany. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 269–278). Brussels: Royal Flemish Academy of Belgium.
Abstract: Emergency situations, man-made as well as natural, can differ considerably. However, they share the characteristic of sudden onset, involve complex decisions and necessitate a coherent and effective emergency management. In the event of a nuclear or radiological accident in Europe, the real-time on-line decision support system RODOS provides support from the early phase through to the medium and long-term phases. This paper describes the demands to a Decision Support System from a user-centred view as well as experiences gained from conducting moderated decision making workshops based on a hypothetical accident scenario focusing on the evaluation of long-term countermeasures using the simulation capabilities of the RODOS system and its recently integrated evaluation component Web-HIPRE, a tool for multi-criteria decision analysis (MCDA).
|
Felix Riedel, & Fernando Chaves. (2012). Workflows and decision tables for flexible early warning systems. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Today's decision support systems for crisis management are mostly designed to support a fixed process that integrates a given set of information sources. This means policies that govern the crisis management process are tightly integrated with the implementation, which makes it hard to adapt the system to changing requirements. Modern systems are expected to be adaptable and need to evolve along with the availability of new information sources and changing business processes. Previous work suggested using workflow systems to manage crisis management processes. Current approaches that use workflow systems are not end-user friendly or not flexible enough. In this paper we present our approach that combines workflows and decision tables for creating more flexible decision support systems. While workflows are used to orchestrate services and implement information logistics in the decision support processes, embedded rule sets are used to provide flexibility and adaptability of workflows. The rule sets are authored using decision tables which are an easy-to-use representation that allows end-users to express rules in an intuitive way. © 2012 ISCRAM.
|
Eli Rohn, & Gil Erez. (2012). Fighting agro-terrorism in cyberspace: A framework for intention detection using overt electronic data sources. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Agro Terrorism is “a hostile attack, towards an agricultural environment, including infrastructures and processes, in order to significantly damage national and international political interests”. This special session within the early warning track is aimed at reducing agro-terrorism related risks by either means of prevention (intelligence gathering using data mining and chatter mining, for example) or means to response to such an attack by early detection of exotic/foreign pathogenic agents, early prediction of disease dispersion patterns, implementation of biosecurity measures, and the development of future methodologies and techniques related to food defense and post-event response. This paper focuses on intention detection using overt data sources on the World Wide Web as they relate to agro-terrorism threats. The paper focuses on early detection that can lead to prevention of such acts, yet a variety of the techniques presented here are also useful for helping in post-event perpetrators detection. © 2012 ISCRAM.
|
Hussain Aziz Saleh. (2005). Dynamic optimisation of the use of space technology for rapid disaster response and management. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 139–141). Brussels: Royal Flemish Academy of Belgium.
Abstract: Modern space and information technologies provide valuable tools for the solution of many real-world problems in fields of managing effects of natural and man-made disasters, geomatic engineering, etc. Therefore, the need to develop and optimise the use of these technologies in an efficient manner is necessary for providing reliable solutions. This paper aims to develop powerful optimisation algorithms extending current highly successful ideas of artificial intelligence for developing of the disaster warning network which is a system of satellites and ground stations for providing real time early warning of the impact of the disaster and minimise its effects (e.g., earthquakes, landslides, floods, volcanoes, etc). Such intelligent algorithms can provide a degree of functionality and flexibility suitable both for constructing high-accuracy models and in monitoring their behaviour in real time.
|
Axel Schulz, Tung Dang Thanh, Heiko Paulheim, & Immanuel Schweizer. (2013). A fine-grained sentiment analysis approach for detecting crisis related microposts. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 846–851). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Real-time information from microposts like Twitter is useful for applications in the crisis management domain. Currently, that potentially valuable information remains mostly unused by the command staff, mainly because the sheer amount of information cannot be handled efficiently. Sentiment analysis has been shown as an effective tool to detect microposts (such as tweets) that contribute to situational awareness. However, current approaches only focus on two or three emotion classes. But using only tweets with negative emotions for crisis management is not always sufficient. The amount of remaining information is still not manageable or most of the tweets are irrelevant. Thus, a more fine-grained differentiation is needed to identify relevant microposts. In this paper, we show the systematic evaluation of an approach for sentiment analysis on microposts that allows detecting seven emotion classes. A preliminary evaluation of our approach in a crisis related scenario demonstrates the applicability and usefulness.
|
Peter Serwylo, Paul Arbon, & Grace Rumantir. (2011). Predicting patient presentation rates at mass gatherings using machine learning. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Mass gatherings have been defined as events where more than 1,000 people are present for a defined period of time. Such an event presents specific challenges with respect to medical care. First aid is provisioned on-site at most events in order to prevent undue strain on the local emergency services. In order to allocate enough resources to deal with the expected injuries, it is important to be able to accurately predict patient volumes. This study used machine learning techniques to identify which variables are the most important in predicting patient volumes at mass gatherings. Data from 201 mass gatherings across Australia was analysed, finding that event type is the most predictive variable, followed by the state or territory, heat index, humidity, whether it is bounded, and the time of day. Variables with little bearing on the outcome included the presence of alcohol, whether the event was indoors or outdoors, and whether it had one point of focus. The best predictive models produced acceptable predictions of the patient presentations 80% of the time, and this could be further improved using optimization techniques.
|
Huizhang Shen, & Jidi Zhao. (2010). Decision-making support based on the combination of CBR and logic reasoning. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In recent years, various crises arise frequently and cause tremendous economic and life losses. Meanwhile, current emergency decision models and decision support systems still need further improvement. This paper first proposes a new emergency decision model based on the combination of a new case retrieval algorithm for Case-Based Reasoning (CBR) and logic reasoning, and then address a sample flood disaster emergency decision process to explain the application of the model in practice.
|
Huizhang Shen, Jingwen Hu, Jidi Zhao, & Jing Dong. (2012). Ontology-based modeling of emergency incidents and crisis management. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: With the frequent occurrence of emergency incidents in recent years, developing intelligent and effective decision support systems for emergency response and management is getting crucial to the government and public administration. Prior research has made many efforts in constructing crisis databases over the decades. However, existing emergency management systems built on top of these databases provide limited decision support capabilities and are short of information processing and reasoning. Furthermore, ontology based on logic description and rules has more semantics description capability compared to traditional relational database. Aiming to extend existing studies and considering ontology's reusability, this paper presents an approach to build ontology-based DSSs for crisis response and management. © 2012 ISCRAM.
|
André Simões, Armanda Rodrigues, Patricia Pires, & Luis Sá. (2011). Evaluating emergency scenarios using historic data: Flood management. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The evaluation of an emergency scenario is often based on the use of simulation models. The specificity of these models involves the need for a complex evaluation of the problem domain, including the physical conditions behind the considered threat. Based on emergency occurrences data, provided by the Portuguese National Civil Protection Authority, we are currently developing a methodology for evaluating a real situation, based on past occurrences. The aim is to develop a platform that will enable the evaluation of a risk scenario based on existing civil protection data. The methodology under development should enable the evaluation of different scenarios based on the collected available data. This will be achieved thanks to the facilitated configuration of several aspects, such as the geographical region and relevant properties of the considered threat. In this paper, we describe the methodology development process and the current state of the platform for risk evaluation.
|
Alexander Smirnov, Tatiana Levashova, & Nikolay Shilov. (2013). Context-based knowledge fusion patterns in decision support system for emergency response. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 597–606). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: The purpose of this paper is discovery of context-based knowledge fusion patterns. Knowledge fusion is considered as an appearance of new knowledge in consequence of processes ongoing in decision support systems. The knowledge fusion processes are considered within a system intended to support decisions on planning emergency response actions. The knowledge fusion patterns are generalized with regard to preservation of internal structures and autonomies of information and knowledge sources involved in the knowledge fusion and to knowledge fusion results. The found patterns give a general idea of knowledge fusion processes taking place at the operational stage of decision support system functioning, i.e. the stage where context-aware functions of the system come into operation. As a practical application, such patterns can support engineers with making choice of knowledge sources to be used in the systems they design.
|
Kate Starbird, & Jeannie Stamberger. (2010). Tweak the tweet: Leveraging microblogging proliferation with a prescriptive syntax to support citizen reporting. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In this paper, we propose a low-tech solution for use by microbloggers that could enhance their ability to rapidly produce parsable, crisis-relevant information in mass emergencies. We build upon existing research on the use of social media during mass emergencies and disasters. Our proposed intervention aims to leverage the affordances of mobile microblogging and the drive to support citizen reporting within current behavioral Twitter-based microblogging practice. We introduce a prescriptive, tweet-based syntax that could increase the utility of information generated during emergencies by gently reshaping current behavioral practice. This offering is grounded in an understanding of current trends in norm evolution of Twitter use, an evolution that has progressed quickly but appears to be stabilizing around specific textual conventions.
|
Kate Starbird, & Leysia Palen. (2010). Pass it on?: Retweeting in mass emergency. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: We examine microblogged information generated during two different co-occurring natural hazards events in Spring 2009. Due to its rapid and widespread adoption, microblogging in emergency response is a place for serious consideration and experimentation for future application. Because microblogging is comprised of a set of practices shaped by a number of forces, it is important to measure and describe the diffuse, multiparty information exchange behaviors to anticipate how emergency governance might best play a role. Here we direct consideration toward information propagation properties in the Twitterverse, describing features of information redistribution related to the retweet (RT ) convention. Our analysis shows that during an emergency, for tweets authored by local users and tweets that contain emergency-related search terms, retweets are more likely than non-retweets to be about the event. We note that users are more likely to retweet information originally distributed through Twitter accounts run by media, especially the local media, and traditional service organizations. Comparing local users to the broader audience, we also find that tweet-based information redistribution is different for those who are local to an emergency event.
|
Kate Starbird, Grace Muzny, & Leysia Palen. (2012). Learning from the crowd: Collaborative filtering techniques for identifying on-the-ground Twitterers during mass disruptions. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Social media tools, including the microblogging platform Twitter, have been appropriated during mass disruption events by those affected as well as the digitally-convergent crowd. Though tweets sent by those local to an event could be a resource both for responders and those affected, most Twitter activity during mass disruption events is generated by the remote crowd. Tweets from the remote crowd can be seen as noise that must be filtered, but another perspective considers crowd activity as a filtering and recommendation mechanism. This paper tests the hypothesis that crowd behavior can serve as a collaborative filter for identifying people tweeting from the ground during a mass disruption event. We test two models for classifying on-the-ground Twitterers, finding that machine learning techniques using a Support Vector Machine with asymmetric soft margins can be effective in identifying those likely to be on the ground during a mass disruption event. © 2012 ISCRAM.
|