A Systematic Review of Research on ChatGPT

Abstract

This chapter investigates previous research themes and trending topics related to ChatGPT through a comprehensive analysis of the literature. An automated technique (web-scraping) was deployed to retrieve and compile all existing journal papers, conference proceedings, and book chapters from major publisher databases in the related fields, and the abstracts of the selected articles were quantitatively analysed using a probabilistic topic modeling procedure – the latent Dirichlet allocation (LDA) approach. Based on the topics identified by the LDA model utilizing their most representative terms, 10 research themes and corresponding keywords have emerged in the results. The overall findings indicate that research efforts in this field have primarily focused on performance, user disposition, application practices, and ethical and privacy concerns. A conceptual framework that delineated the relationships between the research issues and opportunities for future research on ChatGPT is also introduced.