Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Social Media Data Mining of Human Behaviour during Bushfire Evacuation

Junfeng Wu, Xiangmin Zhou, Erica Kuligowski, Dhirendra Singh, Enrico Ronchi, Max Kinateder

TL;DR

This paper addresses the limitations of traditional bushfire evacuation data by conducting a systematic scoping review of social media data mining. It adopts a four-step evacuation modelling lens and a three-stage data processing pipeline (collection, cleaning, categorization) to extract evacuation-relevant signals from social platforms. It surveys techniques for data collection, cleaning, and categorization, discusses open problems such as data quality, bias, geolocation, and multimodal data, and outlines future applications including model calibration/validation, emergency communication, personalized training, and resource planning. The work highlights both the opportunities and challenges of leveraging real-time, hyperlocal social media data to improve evacuation planning and hazard response.

Abstract

Traditional data sources on bushfire evacuation behaviour, such as quantitative surveys and manual observations have severe limitations. Mining social media data related to bushfire evacuations promises to close this gap by allowing the collection and processing of a large amount of behavioural data, which are low-cost, accurate, possibly including location information and rich contextual information. However, social media data have many limitations, such as being scattered, incomplete, informal, etc. Together, these limitations represent several challenges to their usefulness to better understand bushfire evacuation. To overcome these challenges and provide guidance on which and how social media data can be used, this scoping review of the literature reports on recent advances in relevant data mining techniques. In addition, future applications and open problems are discussed. We envision future applications such as evacuation model calibration and validation, emergency communication, personalised evacuation training, and resource allocation for evacuation preparedness. We identify open problems such as data quality, bias and representativeness, geolocation accuracy, contextual understanding, crisis-specific lexicon and semantics, and multimodal data interpretation.

Social Media Data Mining of Human Behaviour during Bushfire Evacuation

TL;DR

This paper addresses the limitations of traditional bushfire evacuation data by conducting a systematic scoping review of social media data mining. It adopts a four-step evacuation modelling lens and a three-stage data processing pipeline (collection, cleaning, categorization) to extract evacuation-relevant signals from social platforms. It surveys techniques for data collection, cleaning, and categorization, discusses open problems such as data quality, bias, geolocation, and multimodal data, and outlines future applications including model calibration/validation, emergency communication, personalized training, and resource planning. The work highlights both the opportunities and challenges of leveraging real-time, hyperlocal social media data to improve evacuation planning and hazard response.

Abstract

Traditional data sources on bushfire evacuation behaviour, such as quantitative surveys and manual observations have severe limitations. Mining social media data related to bushfire evacuations promises to close this gap by allowing the collection and processing of a large amount of behavioural data, which are low-cost, accurate, possibly including location information and rich contextual information. However, social media data have many limitations, such as being scattered, incomplete, informal, etc. Together, these limitations represent several challenges to their usefulness to better understand bushfire evacuation. To overcome these challenges and provide guidance on which and how social media data can be used, this scoping review of the literature reports on recent advances in relevant data mining techniques. In addition, future applications and open problems are discussed. We envision future applications such as evacuation model calibration and validation, emergency communication, personalised evacuation training, and resource allocation for evacuation preparedness. We identify open problems such as data quality, bias and representativeness, geolocation accuracy, contextual understanding, crisis-specific lexicon and semantics, and multimodal data interpretation.

Paper Structure

This paper contains 27 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Overview of social media data mining for bushfire evacuation
  3. Trip Generation
  4. Trip Distribution
  5. Modal Split
  6. Traffic Assignment
  7. Relevant Techniques
  8. Data Collection
  9. Critical Analysis $\&$ Trade-offs:
  10. Data Cleaning
  11. Critical Analysis $\&$ Trade-offs:
  12. Data Categorization
  13. Critical Analysis $\&$ Trade-offs:
  14. Applications of social media
  15. Evacuation Model Calibration and Validation
  16. ...and 12 more sections

Figures (4)

  • Figure 1: Pipeline of Social Media Data Mining of Human Behaviour during Bushfire Evacuations
  • Figure 2: Feature Extraction for Collecting Data in Social Media Data Mining of Human Behaviours during Bushfire Evacuations.
  • Figure 3: Features for Cleaning Data in Social Media Data Mining of Human Behaviours during Bushfire Evacuations.
  • Figure 4: Features for Cleaning Data in Social Media Data Mining of Human Behaviours during Bushfire Evacuations.