tkgl_icews — Political events between actors (ICEWS, tkgl-icews, TGB 2.0, 1995-2022)
- Description
A temporal network of political events between socio-political actors (e.g. governments, politicians, organizations, or citizens of a country) worldwide, from January 1995 to December 2022, from the
tkgl-icewsdataset of the Temporal Graph Benchmark (TGB 2.0), based on the Integrated Crisis Early Warning System (ICEWS) coded event data. ICEWS codes events automatically from news stories with the CAMEO taxonomy of event types. Each node is an actor, and each directed edge from actor A to actor B is an event of one of the CAMEO types (e.g. A makes a statement to, consults, accuses, or attacks B), with its date. The events whose source or target is missing were removed by TGB. The actors are anonymized in the data (they are identified only by indices).The network has the following properties:
- (Edge)
relation: the CAMEO code of the type of the event (e.g.051, "praise or endorse", or173, "arrest, detain, or charge with legal action"), see the CAMEO codebook. - (Edge)
time: the date of the event, in Unix time (of midnight in the US Eastern time zone, as given).
- (Edge)
- Tags
- Social Political Conflict Unweighted Multigraph Timestamps Metadata
- Added
- 2026-10-27
- Citation
-
- J. Gastinger, S. Huang, M. Galkin, E. Loghmani, A. Parviz, F. Poursafaei, J. Danovitch, E. Rossi, I. Koutis, H. Stuckenschmidt, R. Rabbany, G. Rabusseau, "TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs." Advances in Neural Information Processing Systems 37 (Datasets and Benchmarks Track) (2024) 10.48550/arXiv.2406.09639 Sci-Hub
- E. Boschee, J. Lautenschlager, S. O'Brien, S. Shellman, J. Starz, M. Ward, "ICEWS Coded Event Data." Harvard Dataverse (2015) 10.7910/DVN/28075 Sci-Hub
- Upstream URL OK
-
https://tgb.complexdatalab.com/docs/tkg/
https://github.com/shenyangHuang/TGB
https://dataverse.harvard.edu/dataverse/icews - Upstream license
- ICEWS custom license: research and educational use only, no commercial use, https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/28075
- Networks
-
Tip: hover over a column header for a description.
Column legend
- $\left<k\right>$
- Mean degree
- $\sigma_k$
- Standard deviation of the degrees
- $\lambda_h$
- Largest eigenvalue of the Hashimoto (non-backtracking) matrix
- $\tau$
- Random walk mixing time
- $r$
- Degree assortativity
- $c$
- Global clustering coefficient
- $\oslash$
- (Pseudo-) diameter
- $S$
- Relative size of the largest component
- NPs
- Node properties
- EPs
- Edge properties