A methodology for identifying breakthrough topics using structural entropy

被引：32
|
作者：
Xu, Haiyun [1 ]
Luo, Rui [2 ]
Winnink, Jos [3 ]
Wang, Chao [4 ]
Elahi, Ehsan [5 ]
机构：
[1] Shandong Univ Technol, Business Sch, Zibo 255000, Peoples R China
[2] Jiangsu Acad Agr Sci, Informat Ctr, Nanjing 210014, Peoples R China
[3] Leiden Univ, Ctr Sci & Technol Studies CWTS, NL-2300 AX Leiden, Netherlands
[4] Shandong Acad Sci, Informat Res Inst, Jinan 250014, Peoples R China
[5] Shandong Univ Technol, Sch Econ, Zibo 255049, Shandong, Peoples R China
来源：
INFORMATION PROCESSING & MANAGEMENT | 2022年 / 59卷 / 02期
基金：
中国博士后科学基金; 中国国家自然科学基金;
关键词：
structural entropy; scientific breakthrough; link prediction; knowledge networks; COMPLEX NETWORKS; SCIENCE; IDENTIFICATION; RECOGNITION;
D O I：
10.1016/j.ipm.2021.102862
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This research uses link prediction and structural-entropy methods to predict scientific breakthrough topics. Temporal changes in the structural entropy of a knowledge network can be used to identify potential breakthrough topics. This has been done by tracking and monitoring a network's critical transition points, also known as tipping points. The moment at which a significant change in the structural entropy of a knowledge network occurs may denote the points in time when breakthrough topics emerge. The method was validated by domain experts and was demonstrated to be a feasible tool for identifying scientific breakthroughs early. This method can play a role in identifying scientific breakthroughs and could aid in realizing forward-looking predictions to provide support for policy formulation and direct scientific research.
引用
收藏
页数：20
相关论文
共 50 条
  • [1] Effective and efficient identifying influential nodes in large scale networks by structural entropy
    Huang, Yuxin
    Li, Chunping
    Xiang, Yan
    Xian, Yantuan
    Li, Pu
    Yu, Zhengtao
    CHAOS SOLITONS & FRACTALS, 2025, 196
  • [2] Breakthrough potential of emerging research topics based on citation diffusion features
    Xu, Haiyun
    Winnink, Jos
    Pang, Hongshen
    Wen, Shuhao
    Chen, Liang
    JOURNAL OF INFORMATION SCIENCE, 2023, 49 (05) : 1390 - 1416
  • [3] Identifying potential breakthrough research: A machine learning method using scientific papers and Twitter data
    Li, Xin
    Wen, Yang
    Jiang, Jiaojiao
    Daim, Tugrul
    Huang, Lucheng
    TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2022, 184
  • [4] Identifying breakthrough scientific papers
    Savov, Pavel
    Jatowt, Adam
    Nielek, Radoslaw
    INFORMATION PROCESSING & MANAGEMENT, 2020, 57 (02)
  • [5] Improving Togetherness Using Structural Entropy
    Zhang, Siyu
    Liu, Jiamou
    Liu, Yiwei
    Zhang, Zijian
    Khoussainov, Bakhadyr
    MOBILE COMPUTING, APPLICATIONS, AND SERVICES, MOBICASE 2021, 2022, 434 : 85 - 98
  • [6] A deep learning approach for identifying biomedical breakthrough discoveries using context analysis
    Wang, Xue
    Yang, Xuemei
    Du, Jian
    Wang, Xuwen
    Li, Jiao
    Tang, Xiaoli
    SCIENTOMETRICS, 2021, 126 (07) : 5531 - 5549
  • [7] Identifying emerging topics in a technological domain
    Zhang, Shengtai
    Han, Fang
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2016, 31 (04) : 2147 - 2157
  • [8] Novel methodology for identifying the weight of moving vehicles on bridges using structural response pattern extraction and deep learning algorithms
    Zhou, Yun
    Pei, Yilin
    Zhou, Sai
    Zhao, Yu
    Hu, Jianxin
    Yi, Weijian
    MEASUREMENT, 2021, 168
  • [9] Identifying structural domains of proteins using clustering
    Feldman, Howard J.
    BMC BIOINFORMATICS, 2012, 13
  • [10] Identifying structural variability using Bayesian inference
    Dwight, R. P.
    Haddad-Khodaparast, H.
    Mottershead, J. E.
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2012) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2012), 2012, : 4681 - 4695
12345