A GPT-Aided literature review process for total quality management and business excellence (2020-2023)

ABSTRACTS

In an era of rapid technological evolution and competitive pressures, Total Quality Management (TQM) requires up-to-date literature reviews to reflect its evolving nature. This study addresses this need through a comprehensive analysis of TQM&BE journal articles from 2020 to 2023 and by introducing the LitRev-GPT framework. The research data was collected from the Scopus database, specifically targeting articles published in the TQM&BE journal from 2020 to 2023. This LitRev-GPT framework employs the Generative Pretrained Transformer (GPT) for efficient categorization and summarization of academic papers, setting new standards for reproducibility and methodological soundness. We identified emergent themes such as ‘Corporate Social Responsibility’, intertwining TQM with ethical practices, and ‘Industry 4.0’, showcasing TQM's adaptability to technological advancements. Additionally, trend analysis highlighted a sustained interest in foundational TQM themes, with a growing emphasis on innovation management. The LitRev-GPT framework demonstrates significant methodological advancements, enhancing the efficiency and depth of literature reviews beyond traditional AI capabilities.

KEYWORDS:

• Total Quality Management (TQM)
• Literature Review
• Generative Pretrained Transformer (GPT)
• Thematic Analysis
• Topic analysis

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 This service, accessible via a web interface, is available for anyone to use free of charge: https://chat.openai.com/

2 https://platform.openai.com/docs/guides/gpt/chat-completions-api

3 For readers interested in the full results of categorization and summaries, feel free to contact the corresponding author via email.

4 For those readers interested in more detailed summaries of each thematic area, please feel free to contact the corresponding author via email.