Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recognizing Similar Crises through the Application of Ontology-based Knowledge Mining

Ngoc Luyen Le, Marie-Hélène Abel, Elsa Negre

TL;DR

The paper addresses the challenge of recognizing similar crisis situations by constructing an ontology-based crisis knowledge base and a semantic similarity measure tailored to crisis-related triples. The approach combines process-cycle data transformation, agile ontology development (AMOD), and RDF/OWL-based representation to enable automated similarity assessment and retrieval of relevant past crises. Experiments leveraging EM-DAT data demonstrate substantial improvements in ontology enrichment and similarity discovery, highlighting the method's potential to enhance crisis recognition and decision-making. Overall, the work offers a principled framework for structured crisis information management and similarity-based reasoning to support crisis response planning.

Abstract

Recognizing and learning from similar crisis situations is crucial for the development of effective response strategies. This study addresses the challenge of identifying similarities within a wide range of crisis-related information. To overcome this challenge, we employed an ontology-based crisis situation knowledge base enriched with crisis-related information. Additionally, we implemented a semantic similarity measure to assess the degree of similarity between crisis situations. Our investigation specifically focuses on recognizing similar crises through the application of ontology-based knowledge mining. Through our experiments, we demonstrate the accuracy and efficiency of our approach to recognizing similar crises. These findings highlight the potential of ontology-based knowledge mining for enhancing crisis recognition processes and improving overall crisis management strategies.

Recognizing Similar Crises through the Application of Ontology-based Knowledge Mining

TL;DR

The paper addresses the challenge of recognizing similar crisis situations by constructing an ontology-based crisis knowledge base and a semantic similarity measure tailored to crisis-related triples. The approach combines process-cycle data transformation, agile ontology development (AMOD), and RDF/OWL-based representation to enable automated similarity assessment and retrieval of relevant past crises. Experiments leveraging EM-DAT data demonstrate substantial improvements in ontology enrichment and similarity discovery, highlighting the method's potential to enhance crisis recognition and decision-making. Overall, the work offers a principled framework for structured crisis information management and similarity-based reasoning to support crisis response planning.

Abstract

Recognizing and learning from similar crisis situations is crucial for the development of effective response strategies. This study addresses the challenge of identifying similarities within a wide range of crisis-related information. To overcome this challenge, we employed an ontology-based crisis situation knowledge base enriched with crisis-related information. Additionally, we implemented a semantic similarity measure to assess the degree of similarity between crisis situations. Our investigation specifically focuses on recognizing similar crises through the application of ontology-based knowledge mining. Through our experiments, we demonstrate the accuracy and efficiency of our approach to recognizing similar crises. These findings highlight the potential of ontology-based knowledge mining for enhancing crisis recognition processes and improving overall crisis management strategies.
Paper Structure (12 sections, 5 equations, 5 figures, 1 table)

This paper contains 12 sections, 5 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Crisis-Related Information Management
  4. Similar Crisis Identification
  5. Our approach
  6. Process Cycle Formulation
  7. Ontology-based Crisis Situation Knowledge Base
  8. Semantic Similarity Measure
  9. Experiments
  10. Enrichment of the Knowledge Base
  11. Measuring Similarity between Crises
  12. Conclusion and Perspectives

Figures (5)

  • Figure 1: A process cycle for recognizing similar crisis situations.
  • Figure 2: A dedicated ontology section for crisis-related information ontology included a hierarchy of crisis types (yellow boxes), damage (orange boxes), physical characteristics (blue boxes), geographical information (green boxes), and temporal entity (violet boxes), ["ico": IsyCri meta-model, "to": Time Ontology].
  • Figure 3: Number of crisis situations that occurred in France, classified by crisis type, from 1903 to 2022
  • Figure 4: Similarity scores of the twelve randomly extracted crisis situations.
  • Figure 5: Comparison heat chart illustrating the similarity scores of our approach and that of li2021ontology