Quantifying and suppressing ranking bias in a large citation network
作者：
Highlights：
• We analyze a large citation network from Microsoft Academic Graph (18193082 papers).
• We introduce a new statistical framework to quantify ranking bias by age and field.
• The new framework allows us to quantify fields’ contribution to ranking bias.
• Existing indicators, including relative citation count and PageRank, are biased.
• We introduce two new indicators that are much less biased than existing indicators.
摘要
•We analyze a large citation network from Microsoft Academic Graph (18193082 papers).•We introduce a new statistical framework to quantify ranking bias by age and field.•The new framework allows us to quantify fields’ contribution to ranking bias.•Existing indicators, including relative citation count and PageRank, are biased.•We introduce two new indicators that are much less biased than existing indicators.
论文关键词：Impact indicators,Ranking,Network analysis,Field bias,Field normalization
论文评审过程：Received 22 March 2017, Revised 22 May 2017, Accepted 28 May 2017, Available online 22 June 2017, Version of Record 22 June 2017.
论文官网地址：https://doi.org/10.1016/j.joi.2017.05.014
