Zachary Neal | Backbone

Network backbones


When a network includes information about the strength of the connections between nodes, it is described as weighted or valued. Weighted networks contain a lot of information, but for this reason can be difficult to visualize and analyze. In some cases, it is useful to extract the backbone of a weighted network that contains only the most important edges. This page provides information about my ongoing work on methods for extracting the network backbones, including information about the backbone package for R.

The backbone package...

The R backbone package implements several methods for extracting the backbone from weighted networks. The package is hosted by CRAN, and can be installed by typing install.packages("backbone") in the R terminal. Once installed, type vignette("backbone_introduction", package = "backbone") to view a detailed description and example of the package's functions.

The current version (1.0.0) focuses on methods for extracting the backbone from weighted networks that are the result of bipartite projections. If you find a bug or want to request a feature, please let us know via our GitHub page.

Related publications...

Neal, Z. P. (In press). A sign of the times? Weak and strong polarization in the U. S. Congress, 1973 – 2016. Social Networks.

  • This paper applies the Stochastic Degree Sequence Model (SDSM) to extract a backbone network of legislators' positive and negative political interactions, using this network to investigate trends in political polarization.

  • Click HERE to get a free copy by email.

Neal, Z. P. (2014). The backbone of bipartite projections: Inferring relationships from co-authorship, co-sponsorship, co-attendance, and other co-behaviors. Social Networks, 39, 84-97.

  • This paper provides an review of several methods used to extract the backbone of weighted networks arise from bipartite projections.

  • Click HERE to get a free copy by email.

Recent & upcoming talks...

21 October 2019 – Rachel Domagalski @ Sci-Files Podcast.

8 November 2019 – Zachary Neal @ MSU Department of Communications  [WATCH THE TALK]

2 December 2019 – Zachary Neal @ Penn State Center for Social Data Analytics (C-SoDA)  [VIEW SLIDES]

00:00 / 01:04

The backbone of the backbone...

Much of this work, and especially the backbone package, is in collaboration with Rachel Domagalski (below, left, human) and Bruce Sagan (below, right) in MSU Mathematics. Portions of it have been generously supported by the National Science Foundation (#1851625).

Ask a question...

Have a question about network backbones, or using the backbone package? Or, are you interested in collaborating on a related project? Or, have you used these methods and want to share the results? Get in touch with me here.

© 2019 by Zachary Neal

  • Twitter Social Icon
  • Amazon Social Icon