Enhancing Bibliometric Insights: A Novel Overlapping Clustering Framework for Citation Networks

• Akhil Veluru

  University of Texas at Dallas

  Author

The primary contribution of this work is the Assembling Overlapping Clusters (AOC) framework, which extends Iterative K-core Clustering (IKC) to produce overlapping clusters for citation networks. AOC retains the original km-valid cores while adding overlapping non-core members, and it does not alter the core-periphery organization of the underlying IKC clusters. AOC creates node-to-cluster memberships by reassigning candidate nodes to additional clusters under either a core-connectivity rule (AOC m) or a relaxed k-link rule (AOC k). This enables the representation of publications with cross-domain relevance without modifying the km-valid cores. AOC operates in a single pass, is order-independent, and preserves the structural integrity of the original IKC output. Applied to a curated extracellular vesicle citation network, AOC increases marker-node coverage and reveals inter-cluster connectivity that is invisible under disjoint clustering.

• PDF

Copyright (c) 2026 International Journal of Intelligent Systems and Data Science

This work is licensed under a Creative Commons Attribution 4.0 International License.