Unbiased evaluation of ranking metrics reveals consistent performance in science and technology citation data
作者：
Highlights：
• We compare the ranking performance of 17 metrics in three distinct citation datasets.
• We use expert-selected items (e.g., seminal papers) to assess the metrics.
• Age biases of the evaluated metrics and the expert-selected items skew the results.
• We argue for an evaluation procedure that explicitly penalizes biased metrics.
• This allows us to uncover metric performance that is consistent across the datasets.
摘要
•We compare the ranking performance of 17 metrics in three distinct citation datasets.•We use expert-selected items (e.g., seminal papers) to assess the metrics.•Age biases of the evaluated metrics and the expert-selected items skew the results.•We argue for an evaluation procedure that explicitly penalizes biased metrics.•This allows us to uncover metric performance that is consistent across the datasets.
论文关键词：Citation networks,Network ranking metrics,Node centrality,Metrics evaluation,Milestone scientific papers and patents
论文评审过程：Received 14 May 2019, Revised 14 December 2019, Accepted 27 December 2019, Available online 4 February 2020, Version of Record 4 February 2020.
论文官网地址：https://doi.org/10.1016/j.joi.2019.101005
