Early identification of scientific breakthroughs through outlier analysis based on research entities  

作　　者：Yang Zhao Mengting Zhang Xiaoli Chen Zhixiong Zhang 

机构地区：[1]National Science Library,Chinese Academy of Sciences,Beijing 100190,China [2]Department of Information Resources Management,School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China

出　　处：《Journal of Data and Information Science》2024年第4期90-109,共20页数据与情报科学学报（英文版）

基　　金：supported by the major project of the National Social Science Foundation of China“Big Data-driven Semantic Evaluation System of Science and Technology Literature”(Grant No.21&ZD329)。

摘　　要：Purpose:To address the“anomalies”that occur when scientific breakthroughs emerge,this study focuses on identifying early signs and nascent stages of breakthrough innovations from the perspective of outliers,aiming to achieve early identification of scientific breakthroughs in papers.Design/methodology/approach:This study utilizes semantic technology to extract research entities from the titles and abstracts of papers to represent each paper’s research content.Outlier detection methods are then employed to measure and analyze the anomalies in breakthrough papers during their early stages.The development and evolution process are traced using literature time tags.Finally,a case study is conducted using the key publications of the 2021 Nobel Prize laureates in Physiology or Medicine.Findings:Through manual analysis of all identified outlier papers,the effectiveness of the proposed method for early identifying potential scientific breakthroughs is verified.Research limitations:The study’s applicability has only been empirically tested in the biomedical field.More data from various fields are needed to validate the robustness and generalizability of the method.Practical implications:This study provides a valuable supplement to current methods for early identification of scientific breakthroughs,effectively supporting technological intelligence decision-making and services.Originality/value:The study introduces a novel approach to early identification of scientific breakthroughs by leveraging outlier analysis of research entities,offering a more sensitive,precise,and fine-grained alternative method compared to traditional citation-based evaluations,which enhances the ability to identify nascent breakthrough innovations.

关 键 词：Scientific breakthroughs Outlier analysis Research entities 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]