Classical Machine Learning: Seventy Years of Algorithmic Learning Evolution

TL;DR

This paper provides a comprehensive bibliometric analysis of classical machine learning algorithms over twelve decades, highlighting influential research, collaboration networks, and emerging trends to inform future developments.

Contribution

It offers the first extensive bibliometric overview of classical ML research, identifying key papers, authors, and evolving themes across twelve decades.

Findings

Identified the most influential papers and authors in ML history.

Mapped the evolution of research themes and collaboration networks.

Highlighted geographic distribution and emerging focus areas in ML.

Abstract

Machine learning (ML) has transformed numerous fields, but understanding its foundational research is crucial for its continued progress. This paper presents an overview of the significant classical ML algorithms and examines the state-of-the-art publications spanning twelve decades through an extensive bibliometric analysis study. We analyzed a dataset of highly cited papers from prominent ML conferences and journals, employing citation and keyword analyses to uncover critical insights. The study further identifies the most influential papers and authors, reveals the evolving collaborative networks within the ML community, and pinpoints prevailing research themes and emerging focus areas. Additionally, we examine the geographic distribution of highly cited publications, highlighting the leading countries in ML research. This study provides a comprehensive overview of the evolution of traditional learning algorithms and their impacts. It discusses challenges and opportunities for future development, focusing on the Global South. The findings from this paper offer valuable insights for both ML experts and the broader research community, enhancing understanding of the field's trajectory and its significant influence on recent advances in learning algorithms.