An Algorithmic Upgrade for Literature Reviews—Tested on Financial Narratives
Literature reviews are slow, manual, and hard to reproduce. This paper unveils an algorithmic framework that uses Natural Language Processing, clustering, and interpretability tools to speed up screening, make choices auditable, and raise the quality of what gets included.
As a test case, the authors mapped research on financial narratives—the collective stories investors tell that can move markets—by mining the Scopus database. The framework auto-clustered papers, surfaced themes, and explained why items were selected, offering a transparent, repeatable SLR pipeline.
- Findings: work on financial narratives is fragmented and often reduced to sentiment analysis or topic modeling, with no unifying theory.
- Implication: the field needs richer, dynamic models of narratives to better connect stories to prices.
- Bonus: the method makes SLRs faster, more consistent, and easier to update.
Read the paper: https://arxiv.org/abs/2601.03794
Paper: https://arxiv.org/abs/2601.03794v1
Register: https://www.AiFeta.com
#NLP #SystematicReview #AI #ResearchMethods #Finance #FinancialNarratives #Reproducibility #Scientometrics
