Social Network Analysis for Startups

Chapter 4. Cliques, Clusters and Components

In the previous chapter, we mainly talked about properties of individuals in a social network. In this chapter, we start working with progressively larger chunks of the network, analyzing not just the individuals and their connection patterns, but entire subgraphs and clusters. We’ll explore what it means to be in a triad and what benefits and stresses can come from being in a structural hole.

First, we will deconstruct the network by progressively removing parts to find its core(s); then, we’ll re-construct the network from its constituent parts—diads, triads, cliques, clans and clusters.

Components and Subgraphs

To start teasing apart the networks into analyzable parts, let us first make a couple definitions:

• A subgraph is a subset of the nodes of a network, and all of the edges linking these nodes. Any group of nodes can form a subgraph—and further down we will describe several interesting ways to use this.

• Component subgraphs (or simply components) are portions of the network that are disconnected from each other. Before the meeting of Romeo and Juliet, the two families were quite separate (save for the conflict ties), and thus could be treated as components.

Many real networks (especially these collected with random sampling) have multiple components. One could argue that this is a sampling error (which is very possible)—but at the same time, it may just mean that the ties between components are outside of the scope of the sampling and ...