Article: Causality mining for historical events based on knowledge graphs Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.35 pp.74 - 88 Abstract: This study proposes a novel probabilistic inference framework leveraging knowledge graphs (KG) to address sparsity and implicitness challenges in historical event causality. Key innovations include a dynamic event embedding (DEE) model incorporating a temporal decay factor <i>β</i> to capture the dynamic weakening of causal strength over time, and a causal graph neural network (CauGNN) utilising directional propagation and cross-event attention for modelling causal transmission between discontinuous events. Evaluated on the event-centric knowledge graph (EventKG) dataset spanning centuries, the method achieves 89.2% causal inference accuracy - a significant 12.7% improvement over state-of-the-art approaches - and a low temporal prediction deviation of 5.2 years. This work establishes a mathematical model for historical causal decay, shifts computational historiography toward quantitative causal reasoning, and provides verifiable tools for historical analysis, education (via the HistVis platform), and societal risk extrapolation. Inderscience Publishers - linking academia, business and industry through research

Title: Causality mining for historical events based on knowledge graphs

Authors: Xin Li

Addresses: Faculty of History and Archaeology, Anyang Normal University, Anyang, 455000, China

Abstract: This study proposes a novel probabilistic inference framework leveraging knowledge graphs (KG) to address sparsity and implicitness challenges in historical event causality. Key innovations include a dynamic event embedding (DEE) model incorporating a temporal decay factor β to capture the dynamic weakening of causal strength over time, and a causal graph neural network (CauGNN) utilising directional propagation and cross-event attention for modelling causal transmission between discontinuous events. Evaluated on the event-centric knowledge graph (EventKG) dataset spanning centuries, the method achieves 89.2% causal inference accuracy - a significant 12.7% improvement over state-of-the-art approaches - and a low temporal prediction deviation of 5.2 years. This work establishes a mathematical model for historical causal decay, shifts computational historiography toward quantitative causal reasoning, and provides verifiable tools for historical analysis, education (via the HistVis platform), and societal risk extrapolation.

Keywords: causal inference; knowledge graph; dynamic event embedding; DEE; historical event analysis.

DOI: 10.1504/IJICT.2025.149049

International Journal of Information and Communication Technology, 2025 Vol.26 No.35, pp.74 - 88

Received: 05 Jul 2025
Accepted: 15 Aug 2025
Published online: 10 Oct 2025 *

Title: Causality mining for historical events based on knowledge graphs

Keep up-to-date