A multi-modal approach towards mining social media data during natural disasters - A case study of Hurricane Irma

Mohanty, Somya D.; Biggers, Brown; Sayedahmed, Saed; Pourebrahim, Nastaran; Goldstein, Evan B.; Bunch, Rick; Chi, Guangqing; Sadri, Fereidoon; McCoy, Thomas P.; Cosby, Arthur G.

doi:10.1016/j.ijdrr.2020.102032

Cited by 23 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the data vary in structure, have high velocity, and are supplied in large quantities, which increases the challenge of obtaining valuable information. Second, the data exist in overwhelming quantities and are difficult for humans to process; manual processing would require significant time, which cannot meet the requirements imposed by real‐time dynamic decision‐making (Guo et al., 2020; Hao & Wang, 2020; Mohanty et al., 2021; Stock, 2018). Finally, traditional search engines might not explore the spatial relations among different geo‐tagged information across different webpages.…”

Section: Event Backgroundmentioning

confidence: 99%

Integrating user‐generated content to track urban flooding hotspots and foster emergency management: A case study in central China

Zeng

Lan

Jiang

et al. 2021

Transactions in GIS

View full text Add to dashboard Cite

This study explores the potential for employing user‐generated content (UGC) during severe flooding to discover and track urban flooding disaster hotspots in a timely manner. A flooding case in central China was selected for this study. Crawlers, natural language processing, and geographic visualization methods were used to extract flood‐related UGC specific to severely flooded areas. Further, the quality of the geo‐tagged content on the web was verified using scientific gauge data (e.g., water level, digital elevation model, and rainfall). Based on our findings, we were able to deduce that UGC on the web is valuable for identifying flooding hotspots. In fact, this approach offers substantial advantages for addressing the emerging needs of data acquisition for flood emergency management. Notably, the values of urban stakeholders that share their observations on the web can be mined rapidly through the integration of various approaches. Overall, the findings of our study can contribute to the efficient mining of web data sources and development of disaster hotspot mapping systems at an urban scale to improve flood management and mitigation. The limitations of UGC and our study's future direction are also discussed.

show abstract

Section: Event Backgroundmentioning

confidence: 99%

Integrating user‐generated content to track urban flooding hotspots and foster emergency management: A case study in central China

Zeng

Lan

Jiang

et al. 2021

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…One option is to try to fuse these images with other existing data sources to develop ground‐truth data sets. For example, linking images with colocated field observations (e.g., Anarde et al., 2020; Coogan et al., 2019; Reeves et al., 2021), numerical model experiments (e.g., Gharagozlou et al., 2020), poststorm damage surveys (e.g., Kennedy et al., 2020; Zhai & Peng, 2020), or social media messages (Mohanty et al., 2021). Ground‐truth data can be used to assess whether the human labels are able to identify past processes from images.…”

Section: Discussionmentioning

confidence: 99%

Labeling Poststorm Coastal Imagery for Machine Learning: Measurement of Interrater Agreement

Goldstein

Buscombe

Lazarus

et al. 2021

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, this could not be enough, especially if people are not aware how to distinguish between good and bad or fake information. Imran et al 2015 [83] and Mohanty et al 2021 [97] have underlined that a solution could be the adoption of automatic/data learned models to draw and filter information.…”

Section: Quality Of Information and Reliabilitymentioning

confidence: 99%

Framing Disaster Risk Perception and Vulnerability in Social Media Communication: A Literature Review

et al. 2022

View full text Add to dashboard Cite

The paper presents the results of a literature review on how social media can impact on disaster risk perception and vulnerability and how these two aspects are interconnected, trying to understand what factors have consequences especially on informational vulnerability. The paper answers to the increasing requests at an international level to move from a technocratic approach to disaster risk management and reduction to a holistic one, where social perspective is integrated. The paper states that this change of paradigm is relevant, especially considering the role that new technologies in communication and information systems are acquiring in disaster risk management and reduction. What emerges from the literature review is that there is a limited scientific production on the topic and further works are desired, to improve knowledge on how new communication and information technologies can impact on vulnerability and risk perception. Furthermore, the two topics are usually discussed separately. However, the role that risk perception can have in increasing or reducing vulnerability deserves to be better discussed.

show abstract

A multi-modal approach towards mining social media data during natural disasters - A case study of Hurricane Irma

Cited by 23 publications

References 30 publications

Integrating user‐generated content to track urban flooding hotspots and foster emergency management: A case study in central China

Integrating user‐generated content to track urban flooding hotspots and foster emergency management: A case study in central China

Labeling Poststorm Coastal Imagery for Machine Learning: Measurement of Interrater Agreement

Framing Disaster Risk Perception and Vulnerability in Social Media Communication: A Literature Review

Contact Info

Product

Resources

About