AI evidence extraction

Natural language processing enhanced literature reviews

Dapeng Liu, Manoj A. Thomas, Li Yan · Journal of Information Technology · 2025

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

1/4

Quality (LMQS)

Evidence

Citations

5.11

FWCI

Top 10%

Impact

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.1177/02683962251371062

Methodology & findings

Study design

Theoretical framework development with literature analysis.

Main result

The study identified "four meta-requirements that underpin the development of effective NLP-enhanced literature review solutions, forming the foundation of our proposed NLP-enhanced Literature Review (NLP-e-LR) framework." The framework "provides structured guidance for applying suitable NLP techniques across various types of literature reviews based on research objectives and review focus" and presents "a mapping of NLP-e-LR process enhancements to the core literature review tasks (i.e., search, screening, and analysis), outlining a range of NLP capabilities aligned with each task."

Reports effect sizes.

Research paradigm

Interpretive/qualitative analysis of literature and frameworks

Author conclusions

The authors conclude that "Recent advances in natural language processing (NLP) and increased computational power have made it easier for researchers to review large volumes of literature more efficiently" and demonstrate "how NLP-e-LR facilitates key literature review activities" through illustrative examples while discussing future research directions.

Limitations

The authors discuss "the benefits and limitations of the framework" but specific limitations are not explicitly detailed in the abstract provided
The paper states it will "identify directions for future research," suggesting acknowledged constraints.

Open questions raised

The paper identifies directions for future research and discusses limitations of the proposed framework, though specific gaps are not enumerated in the abstract.
The authors identify "directions for future research" regarding the framework's benefits and limitations, though specific gaps are not detailed in the provided abstract.
The authors identify "directions for future research" related to the benefits and limitations of the NLP-e-LR framework, though specific gaps are not detailed in the abstract.

Data: not_statedCode: not_statedExtracted from: pdfAgreement 78%

Explore related topics

Systematic Review Automation Literature Discovery Conceptual