Is it all bafflegab? – Linguistic and meta characteristics of research articles in prestigious economics journals
作者：
Highlights：
• This study investigates whether linguistic and meta characteristics of journal articles in economics are associated with scientific prestige.
• Prestige is operationalized as the normalized SCImago Journal Rank (SJR) of the journal that the article was published in.
• The data set of over 200,000 articles is segmented into topically homogeneous clusters using an LDA topic model.
• Beta regression models are estimated using componentwise gradient boosting to determine the most important correlates of scientific prestige.
• In summary, several linguistic and meta features are found to be associated with scientific prestige consistently across clusters.
摘要
•This study investigates whether linguistic and meta characteristics of journal articles in economics are associated with scientific prestige.•Prestige is operationalized as the normalized SCImago Journal Rank (SJR) of the journal that the article was published in.•The data set of over 200,000 articles is segmented into topically homogeneous clusters using an LDA topic model.•Beta regression models are estimated using componentwise gradient boosting to determine the most important correlates of scientific prestige.•In summary, several linguistic and meta features are found to be associated with scientific prestige consistently across clusters.
论文关键词：Research impact,SJR indicator,NLP,Readability,Gradient boosting,GLMLSS
论文评审过程：Received 15 March 2021, Revised 7 March 2022, Accepted 23 March 2022, Available online 5 April 2022, Version of Record 5 April 2022.
论文官网地址：https://doi.org/10.1016/j.joi.2022.101284
