Discovering discoveries: Identifying biomedical discoveries using citation contexts
作者：
Highlights：
• 46% of the articles receiving citances containing “discovery” words are scientific discoveries.
• Eight percent of the articles having 20 or more discovery citances resulted in a Nobel Prize.
• One-third of the articles on the list were co-cited as independent multiple discoveries.
• Discovery recognition can begin early on and peaks after two decades with delays for some articles.
• Machine learning can automate discovery identification with an accuracy and F1 value of 94%.
摘要
•46% of the articles receiving citances containing “discovery” words are scientific discoveries.•Eight percent of the articles having 20 or more discovery citances resulted in a Nobel Prize.•One-third of the articles on the list were co-cited as independent multiple discoveries.•Discovery recognition can begin early on and peaks after two decades with delays for some articles.•Machine learning can automate discovery identification with an accuracy and F1 value of 94%.
论文关键词：Discovery,Biomedicine,Citation contexts,Citances,Machine learning,Pubmed central
论文评审过程：Received 25 August 2016, Revised 12 October 2016, Accepted 6 November 2016, Available online 19 November 2016, Version of Record 19 November 2016.
论文官网地址：https://doi.org/10.1016/j.joi.2016.11.001
