Dilini Rajapaksha, Kacper Sokol, Jeffrey Chan, Flora Salim, Mukesh Prasad, & Mahendra Samarawickrama. (2023). Analysing Donors’ Behaviour in Non-profit Organisations for Disaster Resilience. In V. L. Thomas J. Huggins (Ed.), Proceedings of the ISCRAM Asia Pacific Conference 2022 (pp. 258–267). Palmerston North, New Zealand: Massey Unversity.
Abstract: With the advancement and proliferation of technology, non-profit organisations have embraced social media platforms to improve their operational capabilities through brand advocacy, among many other strategies. The effect of such social media campaigns on these institutions, however, remains largely underexplored, especially during disaster periods. This work introduces and applies a quantitative investigative framework to understand how social media influence the behaviour of donors and their usage of these platforms throughout (natural) disasters. More specifically, we explore how on-line engagement – as captured by Facebook interactions and Google search trends – corresponds to the donors’ behaviour during the catastrophic 2019–2020 Australian bushfire season. To discover this relationship, we analyse the record of donations made to the Australian Red Cross throughout this period. Our exploratory study reveals that social media campaigns are effective in encouraging on-line donations made via a dedicated website. We also compare this mode of giving to more regular, direct deposit gifting.
|
|
Massimo Cossentino, Davide, rea Guastella, Salvatore Lopes, Luca Sabatucci, & Mario Tripiciano. (2022). From Textual Emergency Procedures to Executable Plans. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 200–212). Tarbes, France.
Abstract: Crisis response and management often involve joint actions among different actors. This is particularly true in cross border cooperation, i.e. when actors belong to different countries. This is the operative context of the NETTUNIT research project, which long-term objective is to provide automatic support to emergency management. Modelling emergency plans is challenging because they are usually written in free-form text, thus in a form that is very far from being automatically processed and executed. In other words, it is non-trivial to define workflows capable of managing and monitoring emergency plans. To complicate the problem, typically an emergency evolves in a highly dynamic environment, so there is the need for run-time adaptation. In this paper, we propose a roadmap for producing executable workflows from emergency free-text plans. We set up our current progress in the project and focus on the sub-problem of identifying a suitable modelling notation. We also propose two improvements with respect to the state of the art: 1) a specific diagram focusing on events, roles and responsibilities in a goal-oriented fashion; 2) some guidelines for depicting the emergency plan at hand with a modelling notation.
|
|
Koki Asami, Shono Fujita, Kei Hiroi, & Michinori Hatayama. (2022). Data Augmentation with Synthesized Damaged Roof Images Generated by GAN. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 256–265). Tarbes, France.
Abstract: The lack of availability of large and diverse labeled datasets is one of the most critical issues in the use of machine learning in disaster prevention. Natural disasters are rare occurrences, which makes it difficult to collect sufficient disaster data for training machine learning models. The imbalance between disaster and non-disaster data affects the performance of machine learning algorithms. This study proposes a generative adversarial network (GAN)- based data augmentation, which generates realistic synthesized disaster data to expand the disaster dataset. The effect of the proposed augmentation was validated in the roof damage rate classification task, which improved the recall score by 11.4% on average for classes with small raw data and a high ratio of conventional augmentations such as rotation of image, and the overall recall score improved by 3.9%.
|
|
Hafiz Budi Firmansyah, Jesus Cerquides, & Jose Luis Fernandez-Marquez. (2022). Ensemble Learning for the Classification of Social Media Data in Disaster Response. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 710–718). Tarbes, France.
Abstract: Social media generates large amounts of almost real-time data which has proven valuable in disaster response. Specially for providing information within the first 48 hours after a disaster occurs. However, this potential is poorly exploited in operational environments due to the challenges of curating social media data. This work builds on top of the latest research on automatic classification of social media content, proposing the use of ensemble learning to help in the classification of social media images for disaster response. Ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. Experimental results show that ensemble learning is a valuable technology for the analysis of social media images for disaster response,and could potentially ease the integration of social media data within an operational environment.
|
|
Tim-Jonathan Huyeng, Timo Bittner, & Uwe Rüppel. (2022). Examining the Feasibility of LoRa-based Monitoring in Large-scale Disaster Response Scenarios. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 541–550). Tarbes, France.
Abstract: Following a natural disaster or other large-scale events which require emergency response assessing and monitoring the situation at hand is of critical importance. However, some infrastructure that is often relied upon such as cellular service or the power grid might be temporarily disrupted or entirely unavailable. In order to be able to still transmit relevant monitoring data gathered from sensors, the use of a low-cost LPWAN with LoRa modulation technique is suggested in the approach presented here. Combined with an analysis of disaster response in Germany the relevant aspects are consolidated in a concept utilizing LoRaWAN with a ChirpStack backend that is easy to set up and entirely independent of external infrastructure. The proposed addition which aims to support disaster control management in Germany is then tested in conjunction with a fictional flooding scenario where an area is monitored with autarkic sensors using LoRaWAN technology.
|
|