The total neighbors metric has to be used when the following hypothesis is reasonable:
The more connected a node is, the more social it is, the more likely it is to receive new links.
When quantifying the likelihood of nodes u and v being connected, we can use the number of nodes belonging to the neighboring set of both nodes:
score(u, v) = | N(u) ∪ N(v) |
Let's understand this formula by considering the following two graphs:
Nodes u and v on the left-hand side of the following diagrams have a lot of connections compared to nodes u and v on the right-hand side. Therefore, nodes u and v on the left-hand side are more likely to accept new connections:
