Artificial intelligence and the conduct of literature reviews
Gerit Wagner, Roman Lukyanenko, Guy Paré · Journal of Information Technology · 2021
AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.
This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.1177/02683962211048201
Methodology & findings
Study design
Narrative literature review with conceptual analysis and research agenda development
Primary method
Design science research methodology (proposed agenda for future work)
Main result
The paper identifies that "AI is beginning to transform traditional research practices in many areas" and specifically notes that "literature reviews stand out because they operate on large and rapidly growing volumes of documents, that is, partially structured (meta)data, and pervade almost every type of paper published in information systems research or related social science disciplines." The authors demonstrate how AI can expedite individual steps of the literature review process.
Research paradigm
Constructivism/Design Science
Author conclusions
The authors conclude: "With this agenda, we would like to encourage design science research and a broader constructive discourse on shaping the future of AILRs in research." They propose that AI-based literature reviews represent a significant opportunity for transforming research practices through systematic application of artificial intelligence to traditional review processes.
Limitations
- The paper acknowledges that "the use of AI in this context is in an early stage of development," which inherently limits the maturity and comprehensiveness of available evidence for systematic guidance on AI-based literature reviews.
Open questions raised
- The authors identify the need for comprehensive research on AI-based literature reviews (AILRs), calling for design science research and constructive discourse on how AI can expedite individual steps of the literature review process across information systems and related social science disciplines.
- The authors identify gaps in AI-based literature review methodologies and call for design science research and constructive discourse to develop AILRs, recognizing the early developmental stage of the field and the need for systematic research guidance.
- The authors identify the need for design science research on AI-based literature reviews and call for a broader constructive discourse on shaping the future of AILRs in information systems and related social science research.
Explore related topics
Related papers
- PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and ExplanationAndrea C. Tricco · 2018 · 40,391 citations
- Rayyan—a web and mobile app for systematic reviewsMourad Ouzzani · 2016 · 24,664 citations
- Cochrane Handbook for Systematic Reviews of Interventions2019 · 14,420 citations
- Guidance for conducting systematic scoping reviewsMicah D.J. Peters · 2015 · 7,472 citations
- Updated methodological guidance for the conduct of scoping reviewsMicah D.J. Peters · 2020 · 6,688 citations
- Which academic search systems are suitable for systematic reviews or meta‐analyses? Evaluating retrieval qualities of Google Scholar, PubMed, and 26 other resourcesMichael Gusenbauer · 2019 · 2,116 citations