Early detection of heterogeneous disaster events using social media

Pekar, Viktor; Binner, Jane M.; Najafi, Hossein; Hale, Chris; Schmidt, Vincent A.

doi:10.1002/asi.24208

Cited by 29 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their event detection probability threshold was 0.95. On the other hand, Pekar et al [36] proposed an approach that can detect real-world disaster events from social media data without any prior knowledge about the events. They tackled this issue by implementing a new ensemble method that utilized the available data on the training dataset.…”

Section: Shallow-ml-based Approachesmentioning

confidence: 99%

A Review on the Trends in Event Detection by Analyzing Social Media Platforms’ Data

Mredula

Dey

Rahman

et al. 2022

Sensors

View full text Add to dashboard Cite

Social media platforms have many users who share their thoughts and use these platforms to organize various events collectively. However, different upsetting incidents have occurred in recent years by taking advantage of social media, raising significant concerns. Therefore, considerable research has been carried out to detect any disturbing event and take appropriate measures. This review paper presents a thorough survey to acquire in-depth knowledge about the current research in this field and provide a guideline for future research. We systematically review 67 articles on event detection by sensing social media data from the last decade. We summarize their event detection techniques, tools, technologies, datasets, performance metrics, etc. The reviewed papers mainly address the detection of events, such as natural disasters, traffic, sports, real-time events, and some others. As these detected events can quickly provide an overview of the overall condition of the society, they can significantly help in scrutinizing events disrupting social security. We found that compatibility with different languages, spelling, and dialects is one of the vital challenges the event detection algorithms face. On the other hand, the event detection algorithms need to be robust to process different media, such as texts, images, videos, and locations. We outline that the event detection techniques compatible with heterogeneous data, language, and the platform are still missing. Moreover, the event and its location with a 24 × 7 real-time detection system will bolster the overall event detection performance.

show abstract

Section: Shallow-ml-based Approachesmentioning

confidence: 99%

A Review on the Trends in Event Detection by Analyzing Social Media Platforms’ Data

Mredula

Dey

Rahman

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Various methods exist to differentiate between disaster types within a dataset, however, most consist of an ad hoc review for type-specific terms and phrases within an event report [63,64]. This highlights the importance of identifying terms and phrases that are representative of the subtype of interest [65].…”

Section: An Index For Flood Type Classificationmentioning

confidence: 99%

Development of a Flash Flood Confidence Index from Disaster Reports and Geophysical Susceptibility

Kruczkiewicz

Bucherie

Ayala³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The analysis of historical disaster events is a critical step towards understanding current risk levels and changes in disaster risk over time. Disaster databases are potentially useful tools for exploring trends, however, criteria for inclusion of events and for associated descriptive characteristics is not standardized. For example, some databases include only primary disaster types, such as ‘flood’, while others include subtypes, such as ‘coastal flood’ and ‘flash flood’. Here we outline a method to identify candidate events for assignment of a specific disaster subtype—namely, ‘flash floods’—from the corresponding primary disaster type—namely, ‘flood’. Geophysical data, including variables derived from remote sensing, are integrated to develop an enhanced flash flood confidence index, consisting of both a flash flood confidence index based on text mining of disaster reports and a flash flood susceptibility index from remote sensing derived geophysical data. This method was applied to a historical flood event dataset covering Ecuador. Results indicate the potential value of disaggregating events labeled as a primary disaster type into events of a particular subtype. The outputs are potentially useful for disaster risk reduction and vulnerability assessment if appropriately evaluated for fitness of use.

show abstract

“…These social media data with temporal and spatial attributes have become an important means of understanding public behavior [ 30 ]. Managers and researchers can analyze social media data for disaster detection [ 31 , 32 ], risk communication [ 12 , 33 , 34 , 35 , 36 ], intelligent decision-making [ 37 ], and emergency response [ 38 , 39 ]. For example, government social media can be used for increasing vigilance and awareness in the prodromal stage, disseminating information and increasing transparency in the acute stage, and focusing on mental health support and recovery policies in the chronic stage [ 40 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Capturing the Interplay between Risk Perception and Social Media Posting to Support Risk Response and Decision Making

Zhu

Liu

2021

IJERPH

View full text Add to dashboard Cite

This research aims to capture the interplay between risk perception and social media posting through a case study of COVID-19 in Wuhan to support risk response and decision making. Dividing users on Sina Weibo into the government, the media, the public, and other users, we address two main research questions: Whose posting affects risk perception and vice versa? How do different categories of social media users’ posts affect risk perception and vice versa? We use Granger causality analysis and impulse response functions to answer the research questions. The results show that from one perspective, the government and the media on Sina Weibo play critical roles in forming and affecting risk perceptions. From another perspective, risk perception promotes the posting of the media and the public on Sina Weibo. Since government’s posting and media’s posting can significantly enhance the public’s perceptions of risk issues, the government and the media must remain vigilant to provide credible risk-related information.

show abstract

Early detection of heterogeneous disaster events using social media

Cited by 29 publications

References 18 publications

A Review on the Trends in Event Detection by Analyzing Social Media Platforms’ Data

A Review on the Trends in Event Detection by Analyzing Social Media Platforms’ Data

Development of a Flash Flood Confidence Index from Disaster Reports and Geophysical Susceptibility

Capturing the Interplay between Risk Perception and Social Media Posting to Support Risk Response and Decision Making

Contact Info

Product

Resources

About