An official website of the United States government
Social media platforms are playing increasingly critical roles in disaster response and rescue operations. During emergencies, users can post rescue requests along with their addresses on social media, while volunteers can search for those messages and send help. However, efficiently leveraging social media in rescue operations remains challenging because of the lack of tools to identify rescue request messages on social media automatically and rapidly. Analyzing social media data, such as Twitter data, relies heavily on Natural Language Processing (NLP) algorithms to extract information from texts. The introduction of bidirectional transformers models, such as the Bidirectional Encoder Representations from Transformers (BERT) model, has significantly outperformed previous NLP models in numerous text analysis tasks, providing new opportunities to precisely understand and classify social media data for diverse applications. This study developed and compared ten VictimFinder models for identifying rescue request tweets, three based on milestone NLP algorithms and seven BERT-based. A total of 3191 manually labeled disaster-related tweets posted during 2017 Hurricane Harvey were used as the training and testing datasets. We evaluated the performance of each model by classification accuracy, computation cost, and model stability. Experiment results show that all BERT-based models have significantly increased the accuracy of categorizing rescue-related tweets. The best model for identifying rescue request tweets is a customized BERT-based model with a Convolutional Neural Network (CNN) classifier. Its F1-score is 0.919, which outperforms the baseline model by 10.6%. The developed models can promote social media use for rescue operations in future disaster events.
more »
« less
A Machine Learning Approach for Detecting Rescue Requests from Social Media
Hurricane Harvey in 2017 marked an important transition where many disaster victims used social media rather than the overloaded 911 system to seek rescue. This article presents a machine-learning-based detector of rescue requests from Harvey-related Twitter messages, which differentiates itself from existing ones by accounting for the potential impacts of ZIP codes on both the preparation of training samples and the performance of different machine learning models. We investigate how the outcomes of our ZIP code filtering differ from those of a recent, comparable study in terms of generating training data for machine learning models. Following this, experiments are conducted to test how the existence of ZIP codes would affect the performance of machine learning models by simulating different percentages of ZIP-code-tagged positive samples. The findings show that (1) all machine learning classifiers except K-nearest neighbors and Naïve Bayes achieve state-of-the-art performance in detecting rescue requests from social media; (2) using ZIP code filtering could increase the effectiveness of gathering rescue requests for training machine learning models; (3) machine learning models are better able to identify rescue requests that are associated with ZIP codes. We thereby encourage every rescue-seeking victim to include ZIP codes when posting messages on social media. This study is a useful addition to the literature and can be helpful for first responders to rescue disaster victims more efficiently.
more »
« less
- Award ID(s):
- 1927513
- PAR ID:
- 10470798
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- ISPRS International Journal of Geo-Information
- Volume:
- 11
- Issue:
- 11
- ISSN:
- 2220-9964
- Page Range / eLocation ID:
- 570
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Widespread disasters can overload official agencies’ capacity to provide assistance, and often citizen-led groups emerge to assist with disaster response. As social media platforms have expanded, emergent rescue groups have many ways to harness network and mobile tools to coordinate actions and help fellow citizens. This study used semi-structured interviews and photo elicitation techniques to better understand how wide-scale rescues occurred during the 2017 Hurricane Harvey flooding in the Greater Houston, Texas USA area. We found that citizens used diverse apps and social media-related platforms during these rescues and that they played one of three roles: rescuer, dispatcher, or information compiler. The key social media coordination challenges these rescuers faced were incomplete feedback loops, unclear prioritization, and communication overload. This work-in-progress paper contributes to the field of crisis and disaster response research by sharing the nuances in how citizens use social media to respond to calls for help from flooding victims.more » « less
-
The increasing popularity of multimedia messages shared through public or private social media spills into diverse information dissemination contexts. To date, public social media has been explored as a potential alert system during natural disasters, but high levels of noise (i.e., non-relevant content) present challenges in both understanding social experiences of a disaster and in facilitating disaster recovery. This study builds on current research by uniquely using social media data, collected in the field through qualitative interviews, to create a supervised machine learning model. Collected data represents rescuers and rescuees during the 2017 Hurricane Harvey. Preliminary findings indicate a 99% accuracy in classifying data between signal and noise for signal-to-noise ratios (SNR) of 1:1, 1:2, 1:4, and 1:8. We also find 99% accuracy in classification between respondent types (volunteer rescuer, official rescuer, and rescuee). We furthermore compare human and machine coded attributes, finding that Google Vision API is a more reliable source of detecting attributes for the training set.more » « less
-
The objective of this study is to examine spatial patterns of disaster impacts and recovery of communities based on fluctuations in credit card transactions (CCTs). Such fluctuations could capture the collective effects of household impacts, disrupted accesses, and business closures and thus provide an integrative measure for examining disaster impacts and community recovery. Existing studies depend mainly on survey and sociodemographic data for disaster impacts and recovery effort evaluations, although such data has limitations, including large data collection efforts and delayed timeliness results. Also, there are very few studies have concentrated on spatial patterns of disaster impacts and short-term recovery of communities, although such investigation can enhance situational awareness during disasters and support the identification of disparate spatial patterns of disaster impacts and recovery in the impacted regions. This study examines CCTs data Harris County (Texas, USA) during Hurricane Harvey in 2017 to explore spatial patterns of disaster impacts and recovery duration from the perspective of community residents and businesses at ZIP-code and county scales, respectively, and to further investigate their spatial disparities across ZIP codes. The results indicate that individuals in ZIP codes with populations of higher income experienced more severe disaster impact and recovered more quickly than those located in lower income ZIP codes for most business sectors. Our findings not only enhance the understanding of spatial patterns and disparities in disaster impacts and recovery for better community resilience assessment but also could benefit emergency managers, city planners, and public officials in enhanced situational awareness and resource allocation.more » « less
-
Abstract AI fairness is tasked with evaluating and mitigating bias in algorithms that may discriminate towards protected groups. This paper examines if bias exists in AI algorithms used in disaster management and in what manner. We consider the 2017 Hurricane Harvey when flood victims in Houston resorted to social media to request for rescue. We evaluate a Random Forest regression model trained to predict Twitter rescue request rates from social-environmental data using three fairness criteria (independence, separation, and sufficiency). The Social Vulnerability Index (SVI), its four sub-indices, and four variables representing digital divide were considered sensitive attributes. The Random Forest regression model extracted seven significant predictors of rescue request rates, and from high to low importance they were percent of renter occupied housing units, percent of roads in flood zone, percent of flood zone area, percent of wetland cover, percent of herbaceous, forested and shrub cover, mean elevation, and percent of households with no computer or device. Partial Dependence plots of rescue request rates against each of the seven predictors show the non-linear nature of their relationships. Results of the fairness evaluation of the Random Forest model using the three criteria show no obvious biases for the nine sensitive attributes, except that a minor imperfect sufficiency was found with the SVI Housing and Transportation sub-index. Future AI modeling in disaster research could apply the same methodology used in this paper to evaluate fairness and help reduce unfair resource allocation and other social and geographical disparities.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/ijgi11110570
