ArticleRank is a variant of PageRank whereby the chance of assuming that a link coming from a page with a few outgoing links is more important than others is smaller. This is achieved by introducing the average degree in the formula:
AR(A) = (1 - d) + d * (AR(N1)/(C(N1) + AVG(C)) + ... + AR(Nn)/(C(Nn) + AVG(C)))
Here, AVG(C) is the average number of outgoing connections for all pages in the network.
Usage within GDS is similar to that of PageRank:
CALL gds.alpha.articleRank.stream("projected_graph", {})
YIELD nodeId, score
RETURN gds.util.asNode(nodeId).name as name, score
ORDER BY score DESC
However, the results, as shown here, are much closer to each other:
╒══════════╤═══════╕
│"nodeName"│"score"│
╞══════════╪...