Eigenfactor and Article Influence Score

The Eigenfactor Score and its per-article companion, the Article Influence Score, rank scholarly journals by treating the citation network as a system in which a citation from a prestigious journal counts for more than a citation from an obscure one. Carl Bergstrom introduced the Eigenfactor in 2007 using the same recursive idea behind Google's PageRank: a journal is important if it is cited by other important journals. The score is computed as the stationary distribution of a random walk over the journal-to-journal citation matrix, so it captures not just how often a journal is cited but where those citations come from. The Eigenfactor measures a journal's total influence and therefore scales with size; dividing by the journal's share of articles yields the Article Influence Score, a per-paper measure comparable to a normalized impact factor. West, Bergstrom and Bergstrom set out the full network methodology in 2010.