ArticleRank is an algorithm that has been derived from the PageRank algorithm to measure the influence of journal articles.
Page Rank assumes that relationships originating from low-degree nodes have a higher influence than relationships from high-degree nodes. Article Rank modifies the formula in such a way that it retains the basic PageRank methodology but lowers the influence of low-degree nodes.
The Article Rank of a node v at iteration i is defined as:
Within the formula:
Nin(v) are the incoming neighbors and Nout(v) are the outgoing neighbors of node v.
d is a damping factor in [0, 1], usually set to 0.85.
Nout is the average out-degree
For more information, see ArticleRank: a PageRank‐based alternative to numbers of citations for analysing citation network.
The article rank score for each vertex.
Suppose we have the following graph:
By running Article Rank on the graph, we will see that the vertex with the highest score is Dan:
Name
Description
Data type
v_type
A vertex type.
STRING
e_type
An edge type.
STRING
max_change
Article Rank will stop iterating when the largest difference between any vertex's current score and its previous score ≤ max_change.
That is, the scores have become very stable and are changing by less than max_change
from one iteration to the next.
FLOAT
max_iter
Maximum number of iterations.
INT
damping
The damping factor. Usually set to 0.85.
FLOAT
top_k
The number of results with the highest scores to return.
INT
print_accum
If true, print JSON output.
BOOL
result_attr
If true, store the article rank score of each vertex in this attribute.
STRING
file_path
If true, output CSV to this file.
STRING