Identification of highly-cited papers using topic-model-based and bibliometric features: the consideration of keyword popularity

作者：

Highlights：

• This study examines the effect of keyword popularity (KP) features on prediction of highly-cited papers.

• We use article metadata to calculate KP feature values based on text mining techniques.

• We empirically compared KP features of articles with journal-related and author-related features.

• The results show that, with KP features, the performance of binary classification model can be improved.

摘要

•This study examines the effect of keyword popularity (KP) features on prediction of highly-cited papers.•We use article metadata to calculate KP feature values based on text mining techniques.•We empirically compared KP features of articles with journal-related and author-related features.•The results show that, with KP features, the performance of binary classification model can be improved.

论文关键词：highly-cited papers,keyword popularity,supervised learning,binary classification,topic model

论文评审过程：Received 1 April 2019, Revised 24 December 2019, Accepted 25 December 2019, Available online 13 January 2020, Version of Record 13 January 2020.

论文官网地址：https://doi.org/10.1016/j.joi.2019.101004