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
Evaluating the performance of Deep learning methods for hurricane-related image classification.
Global social media use during natural disasters has been well documented (Murthy et al., 2017). In the U.S., public social media platforms are often a primary venue for those affected by disasters . Some disaster victims believe first responders will see their public posts and that the 9-1-1 telephone system becomes overloaded during crises. Moreover, some feel that the accuracy and utility of information on social media is likely higher than traditional media sources . However, sifting through content during a disaster is often difficult due to the high volume of ‘non-relevant’ content. In addition, text is studied more than images posted on Twitter, leaving a potential gap in understanding disaster experiences. Images posted on social media during disasters have a high level of complexity (Murthy et al., 2016). Our study responds to O’Neal et al.’s (2017) call-to-action that social media images posted during disasters should be studied using machine learning.
more »
« less
- Award ID(s):
- 1760453
- NSF-PAR ID:
- 10120493
- Date Published:
- Journal Name:
- Proceedings of the ... International ISCRAM Conference
- ISSN:
- 2411-3387
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Researchers have established the prominent role digital volunteers play during crises and disasters. From self‐organizing to annotating public data, these volunteers are now a fixture in disaster research. However, we know much less about how these volunteers function, behind the public scene, when using private social media as a disaster unfolds and people need to be rescued. This qualitative study identified the emergent helping roles along with the skillsets and abilities that helped volunteers perform these behind‐the‐scene roles during the Hurricane Harvey flooding in 2017. Using in‐depth interviews along with captured images in private social media, we find these volunteers resembled organizational knowledge workers. We identify nine specific communicating and coordinating actions that these disaster knowledge workers performed. The contributions of these findings centre on implications for disaster response and management.
-
more » « less
Firms’ public communication on social media during disasters can benefit both disaster response efficiency and the perception of the corporate image. Despite its importance, limited guidelines are available to inform firms’ disaster communication strategies. The current study examines firms’ communication on social media in various disasters and how it impacts public engagement. We employ a novel natural language processing (NLP) approach, Semantic Projection with Active Retrieval (SPAR), to analyze Facebook posts made by Russell 3000 firms between 2009 and 2022 concerning various disasters. We show that firm communication can be measured based on two dimensions derived from the Competing Values Framework (CVF): internal versus external and stable versus flexible. We find that social media messages that emphasize operational continuity (internal/stable-oriented) are more popular during biological disasters. By contrast, messages that stress innovations and adaptations to disasters (external/flexible-oriented) elicit more engagement in weather-related disasters. The study offers a framework to characterize and guide firms’ design of disaster communication on social media in different disaster contexts. Our SPAR method is also available to firms to analyze their social media data and uncover the underlying patterns in communication across different contexts.
-
Social media is being increasingly utilized to spread breaking news and updates during disasters of all magnitudes. Unfortunately, due to the unmoderated nature of social media platforms such as Twitter, rumors and misinformation are able to propagate widely. Given this, a surfeit of research has studied rumor diffusion on social media, especially during natural disasters. In many studies, researchers manually code social media data to further analyze the patterns and diffusion dynamics of users and misinformation. This method requires many human hours, and is prone to significant incorrect classifications if the work is not checked over by another individual. In our studies, we fill the research gap by applying seven different machine learning algorithms to automatically classify misinformed Twitter data that is spread during disaster events. Due to the unbalanced nature of the data, three different balancing algorithms are also applied and compared. We collect and drive the classifiers with data from the Manchester Arena bombing (2017), Hurricane Harvey (2017), the Hawaiian incoming missile alert (2018), and the East Coast US tsunami alert (2018). Over 20,000 tweets are classified based on the veracity of their content as either true, false, or neutral, with overall accuracies exceeding 89%.more » « less
-
During natural disasters, people often use social media platforms such as Twitter to ask for help, to provide information about the disaster situation, or to express contempt about the unfolding event or public policies and guidelines. This contempt is in some cases expressed as sarcasm or irony. Understanding this form of speech in a disaster-centric context is essential to improving natural language understanding of disaster-related tweets. In this paper, we introduce HurricaneSARC, a dataset of 15,000 tweets annotated for intended sarcasm, and provide a comprehensive investigation of sarcasm detection using pre-trained language models. Our best model is able to obtain as much as 0.70 F1 on our dataset. We also demonstrate that the performance on HurricaneSARC can be improved by leveraging intermediate task transfer learningmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
