Situational awareness extraction: a comprehensive review of social media data classification during natural hazards

Abstract

Social media (e.g., Twitter and Facebook) can be regarded as vital sources of information during disasters to improve situational awareness (SA) and disaster management since they play a significant role in the rapid spread of information in the event of a disaster. Due to the volume of data is far beyond the capabilities of manual examination, existing works utilize natural language processing methods based on keywords, or classification models relying on features derived from text and other metadata (e.g., user profiles) to extract social media data contributing to SA and automatically categorize them into the relevant classes (e.g., damage and donation). However, the design of the classification schema and the associated information extraction methods are far less than straightforward and highly depend on: (1) the event type, (2) the study or analysis purpose, and (3) the social media platform used. To this end, this paper reviews the literature for extracting social media data and provides an overview of classification schemas that have been used to assess SA in events involving natural hazards from five different analytical perspectives (content, temporal, user, sentiment, and spatiotemporal) by discussing the prevalent topic categories, disaster event types, purpose of studies, and platforms utilized from each schema. Finally, this paper summarizes classification methods, and platforms that are most commonly used for each disaster event type, and outlines a research agenda with recommendations for future innovations.

Disaster Image Classification by Fusing Multimodal Social Media Data

“…It can be seen from the above discussion that a multimodal machine learning method can improve the classification accuracy of disaster images, and the classified data can be applied to solve the problems of disaster assessment and management, such as SA [26]. Specifically, in Task 1, we extracted disaster-related information in order to generate a general awareness of a disaster situation.…”

“…Social media data have been used to conduct various disaster-related studies [26]. Establishing SA is one of the most important purposes of these studies [27].…”

“…It is essential for managers to gather disaster-related information as quickly as possible and to categorize it according to their subject. This will facilitate the implementation of different disaster relief methods, such as providing medical services for injured people, repairing damaged roads, and providing relief supplies for victims [26]. According to the data types, the disaster data classification methods can be divided into two categories: (1) using unimodal data and (2) fusing multimodal data.…”

“…Text-based methods collect text data and mine useful information from social media after a disaster, such as negative crowd sentiment, demands for rescue materials, and emergent rescue requirements among victims [26]. Text-based methods are commonly used to analyze information reliability [7], [28], to classify sentiment [29], and to classify content [30][31][32].…”

Understanding Human Activities in Response to Typhoon Hato from Multi-Source Geospatial Big Data: A Case Study in Guangdong, China

“…In the end, we selected the experiment with 30 topics as the results show the most recognizable keyword groups. We then labeled the topics based on the subcategories of disaster-related topics [61] and grouped the topics into nine major categories based on their parent categories. Finally, as shown in Table 3, we manually labeled samples that were randomly selected from the cleaned microblogs dataset and evaluated the accuracy of the results by using precision, recall, and accuracy (Equations ( 6)-( 8)).…”