- dispersion(G, u=None, v=None, normalized=True, alpha=1.0, b=0.0, c=0.0)[source]#
Calculate dispersion between
A link between two actors (
v) has a high dispersion when their mutual ties (
t) are not well connected with each other.
A NetworkX graph.
- unode, optional
The source for the dispersion score (e.g. ego node of the network).
- vnode, optional
The target of the dispersion score if specified.
If True (default) normalize by the embededness of the nodes (u and v).
- alpha, b, cfloat
Parameters for the normalization procedure. When
normalizedis True, the dispersion value is normalized by:
result = ((dispersion + b) ** alpha) / (embeddedness + c)
as long as the denominator is nonzero.
If u (v) is specified, returns a dictionary of nodes with dispersion score for all “target” (“source”) nodes. If neither u nor v is specified, returns a dictionary of dictionaries for all nodes ‘u’ in the graph with a dispersion score for each node ‘v’.
This implementation follows Lars Backstrom and Jon Kleinberg . Typical usage would be to run dispersion on the ego network \(G_u\) if \(u\) were specified. Running
dispersion()with neither \(u\) nor \(v\) specified can take some time to complete.
Romantic Partnerships and the Dispersion of Social Ties: A Network Analysis of Relationship Status on Facebook. Lars Backstrom, Jon Kleinberg. https://arxiv.org/pdf/1310.6753v1.pdf