Research progress of machine learning: knowledge mapping analysis based on CiteSpace
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
To systematically sort out the research context, hot frontiers, and evolutionary laws in the field of machine learning, this study takes machine learning related literature included in the core collection of CNKI from 2017 to 2026 as the research object, and uses CiteSpace bibliometric tools and knowledge graph visualization methods to conduct in-depth analysis of core dimensions such as keyword co-occurrence, topic clustering, temporal evolution, and emergent words in 1142 effective literature. The research results indicate that the field of machine learning has formed a mature knowledge system with artificial intelligence and deep learning as the core theoretical support, covering multiple dimensions such as algorithm optimization, predictive modeling, and scenario applications; The research evolution presents a third-order characteristic of "theoretical foundation technology integration scenario implementation". From 2017 to 2020, the focus was on basic algorithm verification, from 2021 to 2023, the emphasis was on multi technology cross fusion, and from 2024 to present, breakthroughs in scenario based applications have been highlighted; Explainable artificial intelligence, federated learning, edge computing, small sample learning, etc. are the core frontier directions in the current field. This study presents a clear overview of the research in the field of machine learning through visual graphs, providing important academic references and navigation basis for subsequent scholars to accurately grasp research hotspots and explore innovative directions.
Fields of Study & Subjects
scientometrics and bibliometrics research
Artificial Intelligence Applications
Diverse Approaches in Healthcare and Education Studies
Publication details
- Journal / source
- International Conference on Communication Networks and Machine Learning (CNML)
- Pages
- 1213–1216
- Publication date
- 30 January 2026
- Language
- EN