Dynamic Representations of Global Crises: A Temporal Knowledge Graph for Conflicts, Trade and Value Networks

Julia Gastinger, Timo Sztyler, Nils Steinert, Sabine Gründer-Fahrer, Michael Martin, Anett Schuelke, Heiner Stuckenschmidt
Proceedings of the Third Learning on Graphs Conference, PMLR 269:47:1-47:22, 2025.

Abstract

This paper presents a novel approach to understanding global crises and trade patterns through the creation and analysis of a Temporal Knowledge Graph (TKG), and the application of Temporal Knowledge Graph Forecasting. Combining data from the Armed Conflict Location & Event Data Project (ACLED) and Global Trade Alerts (GTA), the TKG offers a comprehensive view of the intersection between worldwide crises and global trade over time. We detail the process of TKG creation, including the aggregation and merging of information from multiple sources. Furthermore, we conduct a detailed analysis of the TKG, providing insights into its potential applicability to data-driven Resilience Research. Leveraging the constructed TKG, we predict global trade events, such as trade sanctions across various categories and countries, and conflict events, such as worldwide military actions, to identify potential trade disruptions and anticipate the economic impact of global conflicts. To achieve this, state-of-the-art models for TKG Forecasting are applied and rigorously evaluated, contributing to a deeper understanding of the complex relationship between global crises and trade dynamics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v269-gastinger25a, title = {Dynamic Representations of Global Crises: A Temporal Knowledge Graph for Conflicts, Trade and Value Networks}, author = {Gastinger, Julia and Sztyler, Timo and Steinert, Nils and Gr{\"u}nder-Fahrer, Sabine and Martin, Michael and Schuelke, Anett and Stuckenschmidt, Heiner}, booktitle = {Proceedings of the Third Learning on Graphs Conference}, pages = {47:1--47:22}, year = {2025}, editor = {Wolf, Guy and Krishnaswamy, Smita}, volume = {269}, series = {Proceedings of Machine Learning Research}, month = {26--29 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v269/main/assets/gastinger25a/gastinger25a.pdf}, url = {https://proceedings.mlr.press/v269/gastinger25a.html}, abstract = {This paper presents a novel approach to understanding global crises and trade patterns through the creation and analysis of a Temporal Knowledge Graph (TKG), and the application of Temporal Knowledge Graph Forecasting. Combining data from the Armed Conflict Location & Event Data Project (ACLED) and Global Trade Alerts (GTA), the TKG offers a comprehensive view of the intersection between worldwide crises and global trade over time. We detail the process of TKG creation, including the aggregation and merging of information from multiple sources. Furthermore, we conduct a detailed analysis of the TKG, providing insights into its potential applicability to data-driven Resilience Research. Leveraging the constructed TKG, we predict global trade events, such as trade sanctions across various categories and countries, and conflict events, such as worldwide military actions, to identify potential trade disruptions and anticipate the economic impact of global conflicts. To achieve this, state-of-the-art models for TKG Forecasting are applied and rigorously evaluated, contributing to a deeper understanding of the complex relationship between global crises and trade dynamics.} }
Endnote
%0 Conference Paper %T Dynamic Representations of Global Crises: A Temporal Knowledge Graph for Conflicts, Trade and Value Networks %A Julia Gastinger %A Timo Sztyler %A Nils Steinert %A Sabine Gründer-Fahrer %A Michael Martin %A Anett Schuelke %A Heiner Stuckenschmidt %B Proceedings of the Third Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2025 %E Guy Wolf %E Smita Krishnaswamy %F pmlr-v269-gastinger25a %I PMLR %P 47:1--47:22 %U https://proceedings.mlr.press/v269/gastinger25a.html %V 269 %X This paper presents a novel approach to understanding global crises and trade patterns through the creation and analysis of a Temporal Knowledge Graph (TKG), and the application of Temporal Knowledge Graph Forecasting. Combining data from the Armed Conflict Location & Event Data Project (ACLED) and Global Trade Alerts (GTA), the TKG offers a comprehensive view of the intersection between worldwide crises and global trade over time. We detail the process of TKG creation, including the aggregation and merging of information from multiple sources. Furthermore, we conduct a detailed analysis of the TKG, providing insights into its potential applicability to data-driven Resilience Research. Leveraging the constructed TKG, we predict global trade events, such as trade sanctions across various categories and countries, and conflict events, such as worldwide military actions, to identify potential trade disruptions and anticipate the economic impact of global conflicts. To achieve this, state-of-the-art models for TKG Forecasting are applied and rigorously evaluated, contributing to a deeper understanding of the complex relationship between global crises and trade dynamics.
APA
Gastinger, J., Sztyler, T., Steinert, N., Gründer-Fahrer, S., Martin, M., Schuelke, A. & Stuckenschmidt, H.. (2025). Dynamic Representations of Global Crises: A Temporal Knowledge Graph for Conflicts, Trade and Value Networks. Proceedings of the Third Learning on Graphs Conference, in Proceedings of Machine Learning Research 269:47:1-47:22 Available from https://proceedings.mlr.press/v269/gastinger25a.html.

Related Material