More Like this

1. Analyzing Social Media Data to Understand How Disaster-Affected Individuals Adapt to Disaster-Related Telecommunications Disruptions

   Van Wyk, Hannah; Starbird, Kate (May 2020, CoRe Paper – Social Media for Disaster Response and Resilience Proceedings of the 17th ISCRAM Conference)

   McNeill, Fiona; Zobel, Christopher (Ed.)

   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. 

   more » « less
2. Multimodal Semi-supervised Learning for Disaster Tweet Classification

   Iustin Sirbu, Tiberiu Sosea (October 2022, The 29th International Conference on Computational Linguistics (COLING 2022))

   During natural disasters, people often use social media platforms, such as Twitter, to post information about casualties and damage produced by disasters. This information can help relief authorities gain situational awareness in nearly real time, and enable them to quickly distribute resources where most needed. However, annotating data for this purpose can be burdensome, subjective and expensive. In this paper, we investigate how to leverage the copious amounts of unlabeled data generated on social media by disaster eyewitnesses and affected individuals during disaster events. To this end, we propose a semi-supervised learning approach to improve the performance of neural models on several multimodal disaster tweet classification tasks. Our approach shows significant improvements, obtaining up to 7.7% improvements in F-1 in low-data regimes and 1.9% when using the entire training data. We make our code and data publicly available at https://github.com/iustinsirbu13/multimodal-ssl-for-disaster-tweet-classification. 

   more » « less
3. Assessment of the hurricane-induced power outages from a demographic, socioeconomic, and transportation perspective

   https://doi.org/10.1007/s11069-018-3260-9  

   Ulak, Mehmet B.; Kocatepe, A.; Konila Sriram, Lalitha M.; Ozguven, Eren E.; and Arghandeh, R. (July 2018, Natural hazards)

   Natural disasters have devastating effects on the infrastructure and disrupt every aspect of daily life in the regions they hit. To alleviate problems caused by these disasters, first an impact assessment is needed. As such, this paper focuses on a two-step methodology to identify the impact of Hurricane Hermine on the City of Tallahassee, the capital of Florida. The regional and socioeconomic variations in the Hermine’s impact were studied via spatially and statistically analyzing power outages. First step includes a spatial analysis to illustrate the magnitude of customers affected by power outages together with a clustering analysis. This step aims to determine whether the customers affected from outages are clustered or not. Second step involves a Bayesian spatial autoregressive model in order to identify the effects of several demographic-, socioeconomic-, and transportation-related variables on the magnitude of customers affected by power outages. Results showed that customers affected by outages are spatially clustered at particular regions rather than being dispersed. This indicates the need to pinpoint such vulnerable locations and develop strategies to reduce hurricane-induced disruptions. Furthermore, the increase in the magnitude of affected customers was found to be associated with several variables such as the power network and total generated trips as well as the demographic factors. The information gained from the findings of this study can assist emergency officials in identifying critical and/or less resilient regions, and determining those demographic and socioeconomic groups which were relatively more affected by the consequences of hurricanes than others. 

   more » « less
4. Exploring sex differences in information needs, media dependencies, and attention allocation during Hurricane Dorian

   https://doi.org/10.5055/jem.0652  

   Lachlan, PhD; Spence, PhD; Hutter, MA; Gilbert, MA (September 2021, Journal of Emergency Management)

   In September 2019, Hurricane Dorian struck the Bahamas and the southeast United States, resulting in widespread damage and loss of life. Drawing from previous crisis communication research on both natural and man-made disasters, this study examines information seeking and medium preferences, attention allocation, and sex differences in these outcomes. Extant literature has found differences between men and women in terms of the volume and types of information wanted during a crisis event, as well as preferences for different media in times of crisis. This literature has yet to examine the degree to which attention allocation may be related to these outcomes. To address these issues in a naturalistic context, a large-scale survey was targeted at residents of states impacted by Hurricane Dorian. Results are consistent with previous research indicating that females engaged in more overall information seeking and sought more information seeking related to tangible goals. Females found interactive media (Internet and social media) to be more useful than males. Evidence was not detected concerning sex differences in the way people found out about the storm and sex differences in attention allocation detected. Results suggested small effects for perceived usefulness of television and Internet on attention allocation for both men and women. Implications for emergency management personnel and public officials are discussed. 

   more » « less
5. A graph‐based method for social sensing of infrastructure disruptions in disasters

   https://doi.org/10.1111/mice.12457  

   Fan, Chao; Mostafavi, Ali (May 2019, Computer-Aided Civil and Infrastructure Engineering)

   Abstract Damages in critical infrastructure occur abruptly, and disruptions evolve with time dynamically. Understanding the situation of critical infrastructure disruptions is essential to effective disaster response and recovery of communities. Although the potential of social media data for situation awareness during disasters has been investigated in recent studies, the application of social sensing in detecting disruptions and analyzing evolutions of the situation about critical infrastructure is limited. To address this limitation, this study developed a graph‐based method for detecting credible situation information related to infrastructure disruptions in disasters. The proposed method was composed of data filtering, burst time‐frame detection, content similarity calculation, graph analysis, and situation evolution analysis. The application of the proposed method was demonstrated in a case study of Hurricane Harvey in 2017 in Houston. The findings highlighted the capability of the proposed method in detecting credible situational information and capturing the temporal and spatial patterns of critical infrastructure events that occurred in Harvey, including disruptive events and their adverse impacts on communities. The proposed methodology can improve the ability of community members, volunteer responders, and decision makers to detect and respond to infrastructure disruptions in disasters. 

   more » « less