Exploring the use of generative artificial intelligence in systematic searching: A comparative case study of a human librarian, ChatGPT-4 and ChatGPT-4 Turbo

Abstract

The advancement of ChatGPT-powered artificial intelligence (AI) opens up new possibilities for conducting systematic reviews. This study aims to examine how ChatGPT-powered AI can assist in the steps involved in systematic reviews, and its potential and challenges. The authors utilize a comparative case study approach to examine the search-term-generation and article-retrieval capabilities among a human librarian, ChatGPT-4, and a ChatGPT-4 Turbo customized AI-Librarian Bot. The findings suggest that AI could expand the scope of search terms and queries, automating the more repetitive and formulaic aspects of the systematic-review process, while human expertise remains crucial in refining search terms and ensuring methodological rigor. Meanwhile, challenges remain for AI tools’ capacity to access subscription-based or proprietary databases and generate sophisticated search strategies. This study advocates for a synergistic model where AI augments the systematic-review process, complementing the depth and nuance provided by human expertise in achieving accurate and comprehensive research outcomes.