arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.02363cs.DLcs.SI
收藏

$C^3$ -index:重新审视作者的绩效指标

$C^3$-index: Revisiting Authors' Performance Measure

Dinesh Pradhan, Partha Sarathi Paul, Umesh Maheswari, Subrata Nandi, Tanmoy Chakraborty

摘要:

作者绩效指数(如h指数及其变体)在对包括年轻研究人员在内的低指数值(数量上占多数)的作者进行排名时无法解决关系。在这项工作中,我们利用引用以及作者的合作配置文件在一个新的方式使用加权多层网络,并提出了一个变种的页面排名算法,以获得一个新的作者的性能指标,$C^3$索引。在大量出版物数据集上的实验揭示了我们的度量的几个有趣的特征:(i)我们观察到$C^3$-索引随着时间的推移是一致的,(ii)$C^3$ -索引具有很高的潜力,以打破低级别作者之间的联系,(iii)$C^3$ -索引可以有效地用于预测未来的成就在他们的职业生涯的早期阶段。

英文摘要:

Author performance indices (such as h-index and its variants) fail to resolve ties while ranking authors with low index values (majority in number) which includes the young researchers. In this work we leverage the citations as well as collaboration profile of an author in a novel way using a weighted multi-layered network and propose a variant of page-rank algorithm to obtain a new author performance measure, $C^3$-index. Experiments on a massive publication dataset reveal several interesting characteristics of our metric: (i) we observe that $C^3$-index is consistent over time, (ii) $C^3$-index has high potential to break ties among low rank authors, (iii) $C^3$-index can effectively be used to predict future achievers at the early stage of their career.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑