Visualization Inspired by Sankey diagrams and stacked bar charts, this diagram displays changes in Eigenfactor™ Score and clustering over time. The columns corresponds to the years 1997, 1999, 2001, 2003 and 2005. In each year, the journals are grouped vertically according to their cluster structure; within a cluster, they are ordered by their Eigenfactor Score. Bars belonging to the same journal are connected. Clicking highlights both the selected journal over the years, and all clusters it has been part of. This allows to track both changes in journal influence as well as changes in cluster structure. You can see, for instance, the Astrophysical Journal change its cluster from 1997 to 1999.
Data set We use a subset of the citation data from Thomson Reuters' Journal Citation Reports 1997–2005. The complete data aggregate, at the journal level, approximately 60,000,000 citations from more than 7000 journals over the past decade, but here we only display the top 400 journals biennially. For an interesting subset, we select journals ordered by their Article Influence™ in 2005, but include no more than 25 journals from a single field. To make the subset coherent, we make sure that selected journals are included all years and that we cover the 10 journals with highest Eigenfactor Score. To cluster the networks, we use the information-theoretic method presented in Maps of information flow reveal community structure in complex networks ( PNAS 105, 1118 (2008)), which can reveal regularities of information flow across directed and weighted networks.