Exploring Generative Artificial Intelligence Research: A Bibliometric Analysis Approach

Abstract

Artificial Intelligence (AI) and its many applications are changing our lives in ways we could not have imagined a decade ago. Generative artificial intelligence is an artificial intelligence system capable of generating texts, images, and other media based on the input training data. Although still in their early stages, numerous examples of such systems in different domains have gained widespread attention from the public, media, policymakers, and researchers. This study aims to explore the generative AI academic research in the past decade using bibliometrics, text analysis, and social network analysis. Specifically, research themes and their relationships, the evolution of research themes over time, and prominent authors, articles, journals, institutions, and countries publishing in generative AI are identified. The data was further found to partially support the classical bibliometrics laws of Zipf, and Bradford's. The two overarching research themes identified using knowledge synthesis from most cited articles and journals are technical advancements and developments in generative AI systems; and their applications to image processing, pattern recognition, and computer vision. ChatGPT, large language models, and the application of generative AI to healthcare and education are emerging research topics. Additionally, generative AI's usefulness to geoscience, remote sensing, Internet of Things (IoT), and cybersecurity are discussed.