Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications

This repository contains the research poster “Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications”, presented at Advances in Mathematical Finance conference from University of Freiburg in 2025. The work introduces an integrated framework to analyze how U.S. central bank communication evolves around major macroeconomic regime shifts. The approach combines quantitative macroeconomic signal extraction with transformer-based natural language processing to study strategic narrative changes in Federal Reserve speeches during periods of structural economic transition. A composite U.S. Macro Strength Index is constructed using Principal Component Analysis (PCA) on standardized monthly macroeconomic indicators retrieved from FRED, including inflation, growth, labor market, and policy rate variables, covering the period 1996–2025. Structural breaks in the macroeconomic environment are identified through unsupervised change point detection using the PELT algorithm. To study narrative dynamics, Federal Reserve speech transcripts are analyzed across pre- and post-break regimes, with the 2008 financial crisis serving as a primary case study. Topic representations are learned using BERTopic, with partial fitting across regimes to track semantic evolution. Narrative shifts are quantified through sentiment polarity changes, semantic centroid drift, cosine similarity between topic embeddings, and keyword overlap measures based on Maximal Marginal Relevance. Statistical significance is assessed using permutation-based null hypothesis testing, ensuring that observed narrative shifts are not attributable to random temporal reordering. The results reveal clear and statistically significant changes in thematic focus and sentiment orientation that align with detected macroeconomic turning points. The framework provides a transparent and reproducible methodology for monitoring strategic communication in monetary policy and can be extended to other central banks, economic regimes, or policy-relevant textual corpora. Ongoing work explores predictive links between narrative shifts and macroeconomic environment.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-01-07
DOI
https://doi.org/10.5281/zenodo.18167571
Primary Topic
Computational and Text Analysis Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications

Gabin Taibi
Zenodo (CERN European Organization for Nuclear Research)
Computational and Text Analysis Methods
article

Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications

Gabin Taibi
article en

Abstract

This repository contains the research poster “Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications”, presented at Advances in Mathematical Finance conference from University of Freiburg in 2025. The work introduces an integrated framework to analyze how U.S. central bank communication evolves around major macroeconomic regime shifts. The approach combines quantitative macroeconomic signal extraction with transformer-based natural language processing to study strategic narrative changes in Federal Reserve speeches during periods of structural economic transition. A composite U.S. Macro Strength Index is constructed using Principal Component Analysis (PCA) on standardized monthly macroeconomic indicators retrieved from FRED, including inflation, growth, labor market, and policy rate variables, covering the period 1996–2025. Structural breaks in the macroeconomic environment are identified through unsupervised change point detection using the PELT algorithm. To study narrative dynamics, Federal Reserve speech transcripts are analyzed across pre- and post-break regimes, with the 2008 financial crisis serving as a primary case study. Topic representations are learned using BERTopic, with partial fitting across regimes to track semantic evolution. Narrative shifts are quantified through sentiment polarity changes, semantic centroid drift, cosine similarity between topic embeddings, and keyword overlap measures based on Maximal Marginal Relevance. Statistical significance is assessed using permutation-based null hypothesis testing, ensuring that observed narrative shifts are not attributable to random temporal reordering. The results reveal clear and statistically significant changes in thematic focus and sentiment orientation that align with detected macroeconomic turning points. The framework provides a transparent and reproducible methodology for monitoring strategic communication in monetary policy and can be extended to other central banks, economic regimes, or policy-relevant textual corpora. Ongoing work explores predictive links between narrative shifts and macroeconomic environment.

Zenodo (CERN European Organization for Nuclear Research)
University of Twente (NL)
Decent work and economic growth
Openalex Percentile: Top 96%
Computational and Text Analysis Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Strategic Narratives during Economic Turning Points: An AI Framework for Monitoring U.S. Central Bank Communications — Gabin Taibi · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS