A Bibliometric Analysis of Recent Developments and Trends in Knowledge Graph Research (2013-2022)

Knowledge graph has emerged as a useful resource and tool for representing real-world entities and their relations, which gained increasing importance in the fields of deep learning and machine learning. This research aims to investigate the academic publications of knowledge graphs between 2013 and...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 12; p. 1
Main Authors Wang, Gang, He, Jing
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Bibliometric analysis
Bibliometrics
Deep learning
Graphical representations
Graphs
Knowledge graphs
Knowledge representation
Machine learning
Ontologies
Publishing
Research initiatives
Reviews
Scientific publishing
Semantics
Surveys
Systematics
Visual analytics
VOSviewer
Online AccessGet full text

Cover

More Information
Summary:Knowledge graph has emerged as a useful resource and tool for representing real-world entities and their relations, which gained increasing importance in the fields of deep learning and machine learning. This research aims to investigate the academic publications of knowledge graphs between 2013 and 2022 based on the core collection of the Web of Science and examine hot topics and the latest developments in this subject. Thus, the present research adopted a bibliometric analysis to explore the indicators, which mainly focus on different variables from the diachronic productivity of scientific publications to the most prolific countries and the leading publication journals. By means of VOSviewer software, the most productive authors and the frequency of author keywords were further analyzed. The results manifest that dramatic growth has been identified in the past five years due to the output of publications regarding this subject, and the frequently explored themes were mainly conducted from six dimensions, focusing on ontology modelling, knowledge extraction, knowledge graph embedding, graph-based knowledge representation, multi-modal knowledge graphs and knowledge-aware applications. The findings could help researchers to gain a thorough outlook of knowledge graph research, optimize research topic choices, and detect new directions for future studies.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3370409