Prediction of Think Tank Experts' Collaborative Relationships Addressing Complex Issues

Jinxiao Zhu

GBP Proceedings Series, 2025, vol. 10, 56-62

Abstract: Purpose/Significance: Think tank research, as scientific inquiry, spans diverse disciplines. Factors like geography, time, and unfamiliarity hinder efficient expert team formation. Method/Process: This study analyzes/predicts collaboration potential in think tank expert networks to aid team assembly. Addressing the network's scale and rich attributes, we develop IeGNN (Information-exchange Graph Neural Network). It reduces computation by using ego-nets, aggregates neighbor attributes/information via weighted aggregation (using PersonalRank importance), and predicts links via cosine similarity. Result/Conclusion: IeGNN achieved an AUC of 0.9290 on our network, outperforming benchmarks. Case studies on three experts verified its feasibility.

Keywords: think tank; think tank expert cooperation network; link prediction; GNN (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://soapubs.com/index.php/GBPPS/article/view/630/617 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:axf:gbppsa:v:10:y:2025:i::p:56-62

Access Statistics for this article

More articles in GBP Proceedings Series from Scientific Open Access Publishing
Bibliographic data for series maintained by Yuchi Liu ().