What question did this study set out to answer?

The research aims to enhance news event evolution analysis and situation prediction by integrating knowledge graphs with spatio-temporal graph convolutional networks.

April 16, 2026Open Access

A news event evolution analysis and situation prediction model integrating knowledge graphs and spatio-temporal graph convolutional networks

Puntos clave

The research aims to enhance news event evolution analysis and situation prediction by integrating knowledge graphs with spatio-temporal graph convolutional networks.
Developed a model using DE-KG (Dynamic Evolution Knowledge Graph) and semantic-aware ST-GCN (Spatio-Temporal Graph Convolutional Network).
Implemented a dual-modal fusion module for coupling deep semantic and spatio-temporal features.
Conducted experiments to evaluate the model's performance against traditional methods.
Achieved an evolution segmentation F1-score of 0.850, a 20.6% improvement over traditional ST-GCN.
Obtained a situation prediction RMSE of 0.089, a 63.7% improvement compared to the ARIMA model.
Optimal RMSE of 0.083 was specifically noted for public health events.

Resumen

Existing models for news event evolution analysis and situation prediction struggle to balance event semantic dynamics and spatio-temporal feature complexity.Knowledge graphs' static properties cannot capture spatio-temporal evolution patterns, and conventional ST-GCN's insufficient semantic fusion limits prediction accuracy.This study proposes a model integrating DE-KG and semantic-aware ST-GCN; its dual-modal fusion module achieves deep semantic-spatio-temporal feature coupling, improving event evolution analysis and situation prediction.Experiments show the model's evolution segmentation F1-score of 0.850 (+20.6% vs. ST-GCN) and situation prediction RMSE of 0.089 (+63.7% vs. ARIMA, lower decay rate), with an optimal RMSE of 0.083 for public health events.Results verify that DE-KG's semantic dynamics fix static graphs' spatio-temporal gaps, the semantic-aware matrix adapts ST-GCN topology to event semantics, and dual-modal fusion strengthens feature complementarity -greatly improving complex event analysis and prediction performance.

Me gusta

Guardar

Ver artículo completo