知识流动视角下的突破性成果早期识别研究
Research on the Early Identification Method of Breakthrough Achievements from the Perspective of Knowledge Flow
摘要
Abstract
Breakthrough research drives greatly advances in science and technology,and expands the boundaries of human knowledge.The early identification of such achievements is essential for forward-looking basic research plan-ning,the efficient allocation of scientific resources,and the formulation of national innovation strategies.However,ex-isting studies on the identification of breakthrough achievements often focus on a single-dimension rather than an inte-grated theoretical framework,and few adequately explore the early formation mechanisms of breakthrough achieve-ments.To address these limitations,this study proposes a theoretical framework that grounded in knowledge flow theo-ry,encompassing the process of knowledge input,knowledge production,and knowledge output.Based on this frame-work,a multi-dimensional early identification index system comprising 15 indicators is constructed by integrating fea-tures across the three stages.Multiple machine learning algorithms are then employed to build identification models,from which the most effective model is selected.Finally,SHAP is applied to interpret the model and to quantify the relative importance and contributions of different features in the identification process.The results indicate that:① the CatBoost model demonstrates the best performance in early identification.② three key early signals are particularly in-fluential,which are citations within five years,disruption index within five years in the knowledge output stage,and the author's highest academic achievement in the knowledge production stage.③ the model exhibits strong generaliza-tion capability when it verified by APS milestone papers.Overall,this study proposes a novel paradigm that integrates predictive accuracy with interpretability for the early identification of breakthrough research,and provides evidence for understanding its early formation mechanisms.关键词
突破性成果/知识流动理论/早期识别/机器学习/SHAPKey words
Breakthrough achievements/Knowledge flow theory/Early identification/Machine learning/SHAP分类
社会科学引用本文复制引用
叶青,王叶竹,谢云东,张朋..知识流动视角下的突破性成果早期识别研究[J].信息资源管理学报,2026,16(2):111-124,14.基金项目
本文系国家自然科学基金青年科学基金项目"多源数据融合的颠覆性科研成果早期特征提取与识别模型构建"(72404261)、安徽省教育厅科学研究项目"多源融合视角下的学术不端行为关联网络及预测模型研究"(2025AHGXSK40135)和中国科学技术大学新文科基金项目"基于多模态时序语义增强的颠覆性科研成果动态预测及可解释性研究"(FSSF-A-260107)的研究成果之一.(This work is supported by the Youth Project funded by the National Natural Science Foundation of China"Research on Early Feature Extraction and Iden-tification Model Construction of Disruptive Scientific Achievements Based on Multi-source Data Fusion"(72404261),the Scientific Research Project of the Education Department of Anhui Province,China"Research on the Associated Network and Prediction Model of Academic Mis-conduct from a Multi-Source Fusion Perspective"(2025AHGXSK40135),and the New Liberal Arts Fund of USTC"Dynamic Prediction and Ex-plainability of Disruptive Scientific Discoveries Based on Multimodal Temporal Semantic Enhancement"(FSSF-A-260107).) （72404261）
