Detecting technological recombination using semantic analysis and dynamic network analysis

Xiaoli Cao, Xiang Chen, Lu Huang (), Lijie Deng, Yijie Cai and Hang Ren
Additional contact information
Xiaoli Cao: Chinese Academy of Sciences
Xiang Chen: Beijing Institute of Technology
Lu Huang: Beijing Institute of Technology
Lijie Deng: Beijing Institute of Technology
Yijie Cai: Beijing Institute of Technology
Hang Ren: Beijing Institute of Technology

Scientometrics, 2024, vol. 129, issue 11, No 38, 7385-7416

Abstract: Abstract Technological recombinative innovation is a crucial way of innovation, and detecting technological recombination can effectively identify the technical elements with recombinative innovation potential in the future. This study proposes a novel method for detecting technological recombination by combining semantic analysis and dynamic network analysis. The framework accurately captures the hidden semantic changes behind keywords over time and deeply excavates the dynamic evolution characteristics of keyword networks in the development process, which effectively improves the accuracy of the identification results of technological recombination. Firstly, the dynamic word embedding model is applied to generate word vectors, and construct the dynamic keyword networks. Then, the dynamic network link prediction method is trained to predict the future network and the possibility of connection between keywords is calculated, which represents the technological recombination potential value. Finally, in order to identify potential recombination opportunities of crucial technologies in the field, SLM community detection is combined with the PageRank algorithm to identify core keywords in communities of the future network, and then technological recombination candidates corresponding to core keywords are detected. A case study on artificial intelligence domain demonstrates the reliability of the methodology.

Keywords: Technological recombination; Dynamic word embedding; Link prediction; Semantic analysis; Dynamic network analysis (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11192-023-04812-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:scient:v:129:y:2024:i:11:d:10.1007_s11192-023-04812-4

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11192

DOI: 10.1007/s11192-023-04812-4

Access Statistics for this article

Scientometrics is currently edited by Wolfgang Glänzel

More articles in Scientometrics from Springer, Akadémiai Kiadó
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().