|
|
Cornelia Caragea, Adrian Silvescu, & Andrea Tapia. (2016). Identifying Informative Messages in Disasters using Convolutional Neural Networks. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: Social media is a vital source of information during any major event, especially natural disasters. Data produced through social networking sites is seen as ubiquitous, rapid and accessible, and it is believed to empower average citizens to become more situationally aware during disasters and coordinate to help themselves. However, with the exponential increase in the volume of social media data, so comes the increase in data that are irrelevant to a disaster, thus, diminishing peoples? ability to find the information that they need in order to organize relief efforts, find help, and potentially save lives. In this paper, we present an approach to identifying informative messages in social media streams during disaster events. Our approach is based on Convolutional Neural Networks and shows significant improvement in performance over models that use the ?bag of words? and n-grams as features on several datasets of messages from flooding events.
|
|
|
|
Leon J. M. Rothkrantz, & Siska Fitrianie. (2015). Bayesian Classification of Disaster Events on the Basis of Icon Messages of Observers. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: During major disaster events, human operators in a crisis center will be overloaded with under-stress a flood of phone calls. As an increasing number of people in and around big cities do not master the native language, the need for automated systems that automatically process the context and content of information about disaster situations from the communicated messages becomes apparent. To support language-independent communication and to reduce the ambiguity and multitude semantics, we developed an icon-based reporting observation system. Contrast to previous approaches of such a system, we link icon messages to disaster events without using Natural Language Processing. We developed a dedicated set of icons related to the context and characteristic features of disaster events. The developed system is able to compute the probability of the appearance of possible disaster events using Bayesian reasoning. In this paper, we present the reporting system, the developed icons, the Bayesian model, and the results of two experiments.
|
|
|
|
Siska Fitrianie, & Leon J. M. Rothkrantz. (2015). Dynamic Routing during Disaster Events. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: Innovations in mobile technology allow the use of Internet and smartphones for communicating disasters and coordinating evacuations. However, given the turbulent nature of disaster situations, the people and systems at crisis center are subjected to information overload, which can obstruct timely and accurate information sharing. A dynamic and automated evacuation plan that is able to predict future disaster outcome can be used to coordinate the affected people to safety in times of crisis. In this paper, we present a dynamic version of the shortest path algorithm of Dijkstra. The algorithm is able to compute the shortest path from the user?s location (sent by the smartphone) to the safety area by taking into account possible affected areas in future. We aim at employing the computed routes on our mobile communication system for navigating affected people during emergency and disaster evacuations. Two simulation studies have validated the performance of the developed algorithm.
|
|
|
|
Venkata Kishore Neppalli, Murilo Cerqueira Medeiros, Cornelia Caragea, Doina Caragea, Andrea Tapia, & Shane Halse. (2016). Retweetability Analysis and Prediction during Hurricane Sandy. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: Twitter is a very important source for obtaining information, especially during events such as natural disasters. Users can spread information in Twitter either by crafting new posts, which are called ?tweets,? or by using retweet mechanism to re-post the previously created tweets. During natural disasters, identifying how likely a tweet is to be highly retweeted is very important since it can help promote the spread of good information in a network such as Twitter, as well as it can help stop the spread of misinformation, when corroborated with approaches that identify trustworthy information or misinformation, respectively. In this paper, we present an analysis on retweeted tweets to determine several aspects affecting retweetability. We then extract features from tweets? content and user account information and perform experiments to develop models that automatically predict the retweetability of a tweet in the context of the Hurricane Sandy.
|
|
