Randal A. Collins. (2023). Adaptation: A Proposal to Replace Recovery in the Phases of Emergency Management. In V. L. Thomas J. Huggins (Ed.), Proceedings of the ISCRAM Asia Pacific Conference 2022 (pp. 130–137). Palmerston North, New Zealand: Massey Unversity.
Abstract: Mitigation, preparedness, response, and recovery are the four phases of emergency management that have arguably been unchanged since their inception nearly 43 years ago. This paper proposes to replace recovery with adaptation as the post incident phase of emergency management. Recovery focuses on a return to normal while adaptation better encompasses acknowledgement, healing, strengthening, and improving quality of life for a more resilient outcome. This paper reviews seminal work within emergency management and work pertaining to other types of adaptation to better comprehend adaptation as applied to emergency management.
|
|
Hongmin Li, Doina Caragea, & Cornelia Caragea. (2021). Combining Self-training with Deep Learning for Disaster Tweet Classification. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 719–730). Blacksburg, VA (USA): Virginia Tech.
Abstract: Significant progress has been made towards automated classification of disaster or crisis related tweets using machine learning approaches. Deep learning models, such as Convolutional Neural Networks (CNN), domain adaptation approaches based on self-training, and approaches based on pre-trained language models, such as BERT, have been proposed and used independently for disaster tweet classification. In this paper, we propose to combine self-training with CNN and BERT models, respectively, to improve the performance on the task of identifying crisis related tweets in a target disaster where labeled data is assumed to be unavailable, while unlabeled data is available. We evaluate the resulting self-training models on three crisis tweet collections and find that: 1) the pre-trained language model BERTweet is better than the standard BERT model, when fine-tuned for downstream crisis tweets classification; 2) self-training can help improve the performance of the CNN and BERTweet models for larger unlabeled target datasets, but not for smaller datasets.
|
|
Congcong Wang, Paul Nulty, & David Lillis. (2021). Crisis Domain Adaptation Using Sequence-to-Sequence Transformers. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 655–666). Blacksburg, VA (USA): Virginia Tech.
Abstract: User-generated content (UGC) on social media can act as a key source of information for emergency responders incrisis situations. However, due to the volume concerned, computational techniques are needed to effectively filter and prioritise this content as it arises during emerging events. In the literature, these techniques are trained using annotated content from previous crises. In this paper, we investigate how this prior knowledge can be best leveraged for new crises by examining the extent to which crisis events of a similar type are more suitable for adaptation tonew events (cross-domain adaptation). Given the recent successes of transformers in various language processing tasks, we propose CAST: an approach for Crisis domain Adaptation leveraging Sequence-to-sequence Transformers. We evaluate CAST using two major crisis-related message classification datasets. Our experiments show that ourCAST-based best run without using any target data achieves the state of the art performance in both in-domain and cross-domain contexts. Moreover, CAST is particularly effective in one-to-one cross-domain adaptation when trained with a larger language model. In many-to-one adaptation where multiple crises are jointly used as the source domain, CAST further improves its performance. In addition, we find that more similar events are more likely to bring better adaptation performance whereas fine-tuning using dissimilar events does not help for adaptation. To aid reproducibility, we open source our code to the community.
|
|
Hannah Van Wyk, & Kate Starbird. (2020). Analyzing Social Media Data to Understand How Disaster-Affected Individuals Adapt to Disaster-Related Telecommunications Disruptions. 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. 704–717). Blacksburg, VA (USA): Virginia Tech.
Abstract: Information is a critical need during disasters such as hurricanes. Increasingly, people are relying upon cellular and internet-based technology to communicate that information--modalities that are acutely vulnerable to the disruptions to telecommunication infrastructure that are common during disasters. Focusing on Hurricane Maria (2017) and its long-term impacts on Puerto Rico, this research examines how people affected by severe and sustained disruptions to telecommunications services adapt to those disruptions. Leveraging social media trace data as a window into the real-time activities of people who were actively adapting, we use a primarily qualitative approach to identify and characterize how people changed their telecommunications practices and routines--and especially how they changed their locations--to access Wi-Fi and cellular service in the weeks and months after the hurricane. These findings have implications for researchers seeking to better understand human responses to disasters and responders seeking to identify strategies to support affected populations.
|
|
Reza Mazloom, HongMin Li, Doina Caragea, Muhammad Imran, & Cornelia Caragea. (2018). Classification of Twitter Disaster Data Using a Hybrid Feature-Instance Adaptation Approach. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 727–735). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Huge amounts of data that are generated on social media during emergency situations are regarded as troves of critical information. The use of supervised machine learning techniques in the early stages of a disaster is challenged by the lack of labeled data for that particular disaster. Furthermore, supervised models trained on labeled data from a prior disaster may not produce accurate results, given the inherent variation between the current and the prior disasters. To address the challenges posed by the lack of labeled data for a target disaster, we propose to use a hybrid feature-instance adaptation approach based on matrix factorization and the k nearest neighbors algorithm, respectively. The proposed hybrid adaptation approach is used to select a subset of the source disaster data that is representative for the target disaster. The selected subset is subsequently used to learn accurate Naive Bayes classifiers for the target disaster.
|
|