Construction of bipartite and unipartite weighted networks from collections of journal papers

Abstract

This work presents a model that allows the study of research specialties through the manifestations of the specialty's social and epistemological processes in a collection of journal papers. Collections of papers are modeled as coupled bipartite networks interlinking 7 types of entities. Matrix-based link weight functions are introduced to calculate weighted bipartite networks and weighted unipartite co-occurrence networks in the collection of papers. These weight calculation methods, when used in conjunction with unweighted bipartite growth models, produce simple growth models for weighted networks in collections of papers.

18 pages, 16 figures, plus Appendix

References in corpus (5)

• Citation Statistics From More Than a Century of Physical Review
• Minimal models of weighted scale-free networks
• Scale-free properties of weighted networks with connectivity-driven topology
• Bipartite Yule Processes in Collections of Journal Papers
• A weighted evolving network model more approach to reality