Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Linked Data on Geo-annotated Events and Use Cases for the Resilience of Ukraine

Manar Attar, Shuai Wang, Ronald Siebes, Eirik Kultorp, Zhisheng Huang, Tianyang Lu

TL;DR

The paper presents a pipeline to unify geo-annotated damage events from two Ukrainian resilience datasets (EyesOnRussia and Civilian Harm) by converting them into Linked Data, enriching with geospatial information, and merging identical events. A semi-automatic integration algorithm uses spatial distance, description similarity, and shared sources to produce an integrated 10,207-event dataset, enabling rich semantic queries. The authors demonstrate several use cases that highlight visualization, multilingual labeling, timelapse analysis, regional attack patterns, humanitarian indicators, and shelter-gap assessment, illustrating practical resilience applications. Data publication is selective for privacy, with supporting resources and code openly available to facilitate reuse and adaptation to other contexts. The work advances interoperability for resilience analytics by combining ontologies, geospatial enrichment, and cross-dataset reconciliation in a transparent, reusable framework.

Abstract

The mission of resilience of Ukrainian cities calls for international collaboration with the scientific community to increase the quality of information by identifying and integrating information from various news and social media sources. Linked Data technology can be used to unify, enrich, and integrate data from multiple sources. In our work, we focus on datasets about damaging events in Ukraine due to Russia's invasion between February 2022 and the end of April 2023. We convert two selected datasets to Linked Data and enrich them with additional geospatial information. Following that, we present an algorithm for the detection of identical events from different datasets. Our pipeline makes it easy to convert and enrich datasets to integrated Linked Data. The resulting dataset consists of 10K reported events covering damage to hospitals, schools, roads, residential buildings, etc. Finally, we demonstrate in use cases how our dataset can be applied to different scenarios for resilience purposes.

Linked Data on Geo-annotated Events and Use Cases for the Resilience of Ukraine

TL;DR

The paper presents a pipeline to unify geo-annotated damage events from two Ukrainian resilience datasets (EyesOnRussia and Civilian Harm) by converting them into Linked Data, enriching with geospatial information, and merging identical events. A semi-automatic integration algorithm uses spatial distance, description similarity, and shared sources to produce an integrated 10,207-event dataset, enabling rich semantic queries. The authors demonstrate several use cases that highlight visualization, multilingual labeling, timelapse analysis, regional attack patterns, humanitarian indicators, and shelter-gap assessment, illustrating practical resilience applications. Data publication is selective for privacy, with supporting resources and code openly available to facilitate reuse and adaptation to other contexts. The work advances interoperability for resilience analytics by combining ontologies, geospatial enrichment, and cross-dataset reconciliation in a transparent, reusable framework.

Abstract

The mission of resilience of Ukrainian cities calls for international collaboration with the scientific community to increase the quality of information by identifying and integrating information from various news and social media sources. Linked Data technology can be used to unify, enrich, and integrate data from multiple sources. In our work, we focus on datasets about damaging events in Ukraine due to Russia's invasion between February 2022 and the end of April 2023. We convert two selected datasets to Linked Data and enrich them with additional geospatial information. Following that, we present an algorithm for the detection of identical events from different datasets. Our pipeline makes it easy to convert and enrich datasets to integrated Linked Data. The resulting dataset consists of 10K reported events covering damage to hospitals, schools, roads, residential buildings, etc. Finally, we demonstrate in use cases how our dataset can be applied to different scenarios for resilience purposes.
Paper Structure (15 sections, 8 figures, 1 table, 1 algorithm)

This paper contains 15 sections, 8 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Selection
  4. Data Conversion
  5. Data Enrichment
  6. Data Integration
  7. Data Evaluation and Data Publication
  8. Use Cases
  9. Use Case 1: Damage visualization
  10. Use Case 2: Public facilities damaged
  11. Use Case 3: Multilingual representation of labels
  12. Use Case 4: Monthly most attacked regions
  13. Use Case 5: Ratio of children’s death to monthly attacks
  14. Use Case 6: Identifying location without nearby shelters
  15. Discussion and Conclusion

Figures (8)

  • Figure 1: Multilingual representation of the Kupyansk City
  • Figure 2: A visual representation of the damaging events in Kherson
  • Figure 3: Timelapse of events about public facilities
  • Figure 4: YASGUI displaying the top 5 attacked cities in various languages between February 2022 and April 2023
  • Figure 5: Timeline of top 3 most attacked regions monthly
  • ...and 3 more figures