Towards the Utilization of AI-powered Assistance for Systematic Literature Review

Abstract

Systematic literature review (SLR) serves as a cornerstone of evidence-based research, yet its execution often proves time-consuming and labor-intensive. The advent of ChatGPT has sparked interest in harnessing artificial intelligence to streamline various tasks. This paper aims to evaluate the efficacy of two GPT-based tools, Elicit and SciSpace, in automating the SLR process. We assess their usability and reliability in two SLR steps: literature search and citation screening. Through testing via conducted SLR, we examine the benefits and limitations of these tools. Our findings suggest that while Elicit and SciSpace offer significant assistance in literature retrieval and study selection, their integration with human expertise is essential to ensure the thoroughness and accuracy of the review process.