GPT (Generative Pre-trained Transformer) tool in PRISMA literature review

Authors

  • Juliane Silva de Almeida Federal University of Santa Catarina
  • Daniele Cristina Gelain Rezende Federal University of Santa Catarina
  • Fernando Antônio Forcellini Federal University of Santa Catarina

Keywords:

GPT, PRISMA, Academic Research, Knowledge Management, Ethics

Abstract

Technological advances in Learning Language Models (LLM), such as Generative Pre-trained Transformers (GPT), have emerged to synthesize content and improve productivity. After the launch of ChatGPT, developed by OpenAI®, the potential of GPT deployment in a myriad of applications was perceived. One example is in knowledge management for scientific research. However, uncertainty remains about deploying GPT tools to knowledge management for scientific research, avoiding plagiarism, and aiming for productivity. In order to fill this gap, this paper suggests a novel method associating the chatGPT with the Preferred Reported Items for Systematic Review and Meta-analysis (PRISMA) literature review method. Besides that, the GPT's role is to identify the gaps in the literature review regarding the investigated topic and detail the PRISMA analysis. Hence, a prompt application is demonstrated in the results. The contributions of this paper are the prompt suggestions to train the GPT, identify the literature gap, detail the papers’ analysis, and validate the PRISMA research. Therefore, the GPT has the potential of being an academic support tool to enhance the productivity in research done according to its ethical principles.

Downloads

Download data is not yet available.

Published

2025-12-05

How to Cite

Silva de Almeida, J. ., Gelain Rezende, D. C. ., & Forcellini, F. A. . (2025). GPT (Generative Pre-trained Transformer) tool in PRISMA literature review. International Congress of Knowledge and Innovation - Ciki, 1(1). Retrieved from https://proceeding.ciki.ufsc.br/index.php/ciki/article/view/1706