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

• Autores: Xiayu Summer Chen, Yali Feng
• Localización: IFLA journal, ISSN 0340-0352, Vol. 51, Nº. 1, 2025 (Ejemplar dedicado a: [Special Issue: Trends in academic and research libraries]), págs. 84-93
• Idioma: inglés
• DOI: 10.1177/03400352241263532
• Enlaces
  • Texto Completo Ejemplar
• Resumen

  • 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.