Li, H., Caragea, D., Mhatre, A., Ge, J., & Liu, M. (2023). Identifying COVID-19 Tweets Relevant to Low-Income Households Using Semi-supervised BERT and Zero-shot ChatGPT Models. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 953–963). Omaha, USA: University of Nebraska at Omaha.
Abstract: Understanding the COVID-19 pandemic impacts on low-income households can inform social services about the needs of vulnerable communities. Some recent works have studied such impacts through social media content analysis, and supervised machine learning models have been proposed to automatically classify COVID-19 tweets into different categories, such as income and economy impacts, social inequality and justice issues, etc. In this paper, we propose semi-supervised learning models based on BERT with Self-Training and Knowledge Distillation for identifying COVID-19 tweets relevant to low-income households by leveraging readily available unlabeled data in addition to limited amounts of labeled data. Furthermore, we explore ChatGPT’s potential for annotating COVID-19 data and the performance of fine-tuned GPT-3 models. Our semi-supervised BERT model with Knowledge Distillation showed improvements compared to a supervised baseline model, while zero-shot ChatGPT showed good potential as a tool for annotating crisis data. However, our study suggests that the cost of fine-tuning large and expensive GPT-3 models may not be worth for some tasks.
|
|
Borglund, E., A.M., & Granholm, M. (2023). Challenges in work procedures in distributed crisis management. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 732–737). Omaha, USA: University of Nebraska at Omaha.
Abstract: This is a work in progress paper on work and IT usage in distributed crisis management. The data presented in this paper has been collected at a one-day tabletop exercise with four Swedish municipalities. Four members of the four municipalities’ crisis organizations were invited to the exercise, which was designed as one scenario divided into two cases. At the start of each case of the exercise, each municipality was split into two separate rooms, to simulate a distributed crisis management. During the first case they could communicate using phone, TETRA radio, and the Internet. During case two in the scenario, there was no Internet connection. The study indicates that all the municipalities managed to organize and solve the given tasks using primarily voice communication, in case one using phone or, e.g., Teams, and in case two using TETRA radio. Information sharing using IT was non-existing.
|
|
Petrenj, B., Piraina, M., Borghetti, F., Marchionni, G., & Urbano, V. (2023). Cross-border Digital Platform for Transport Critical Infrastructure Resilience: Functionalities and Use Case. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 96–111). Omaha, USA: University of Nebraska at Omaha.
Abstract: The resilience of increasingly interdependent Critical Infrastructure (CI) systems hugely depends on the stakeholder organizations’ ability to exchange information and coordinate, while CI’s cross-border dimension further increases the complexity and challenges. This paper presents the progress in the Lombardy Region (Italy) and Canton Ticino (Switzerland) on the joint capacity to manage disruptive events involving transportation CI between the two countries. We present a cross-border digital platform (Critical Infrastructure Platform – PIC) and its main functionalities for improved cross-border risk and resilience management of CI. A use case, based on a scenario of an intense snowfall along the transboundary motorway impacting both countries, demonstrates how PIC advances the exchange of information, its visualization and analysis in real-time. The use case also shows the practical value of the digital platform and its potential to support the management of cross-border events (and their cascading events) that require the cooperation of Italian and Swiss actors.
|
|
Petersen, L., Havarneanu, G., McCrone, N., & Markarian, G. (2023). Practitioner Perspectives of the PROACTIVE CBRNe Disaster App. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 13–19). Omaha, USA: University of Nebraska at Omaha.
Abstract: To help practitioners better meet the needs of the public at large when managing diverse groups of people during a CBRNe (Chemical, Biological, Radiological, Nuclear and explosive) incident, the PROACTIVE project is developing a CBRNe smartphone disaster app which aims to improve the efficiency of the communication between law enforcement agencies, policy makers and citizens. By using a co-creation methodology with both civil society organisations and CBRNe practitioners, PROACTIVE ensures the app will meet the needs and expectations of both end-user groups. This work-in-progress paper focuses on a workshop carried out with practitioners to test the first mobile app prototype. The results demonstrate that the prototype mobile app is in line with practitioners expectations but that there is room for improvement, such as more visuals, and new features, such as translation, should be added. Looking forward, the app will be updated before being tested in upcoming field training exercises.
|
|
Rahman, S., Ramakrishnan, T., & Ngamassi, L. (2023). Social Media Use for Disaster Management by Underserved Communities: A Uses and Gratification Theory Perspective. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (p. 1074). Omaha, USA: University of Nebraska at Omaha.
Abstract: Social media has emerged as a useful disaster management tool. However, studies indicate that not all individuals are equally inclined towards using social media for managing disasters. Underserved communities have not been able to reap the benefits of social media for disaster management to its full potential. We draw on the Uses and Gratification Theory and the literature on disaster vulnerability of underserved communities to develop a conceptual model. In our poster, we make five propositions in order to examine the motivating factors for the underserved communities to use social media for disaster management.
|
|