Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 20, 2025Open Access

Identifying economic narratives in large text corpora -- An integrated approach using Large Language Models

View Full Paper
Ask AI
Bookmark
Share

Authors

TSTobias M. SchmidtUniversity of GenevaKLKai-Robin LangeTU Dortmund UniversityMRMatthias RecciusRuhr University Bochum

Discussion

Loading...

Member takes

Overview

Analysis reveals large language models extract economic narratives from text, indicating further potential in social sciences.

Key Points

  • GPT-4o can extract economic narratives effectively, but not at expert-level accuracy.
  • The study compares LLM outputs against narratives from expert annotators for validation.
  • Using a complex definition of narratives improves extraction quality from newspaper articles on inflation.
  • Guidance is suggested for future applications of LLMs in economics and social science research.

Cite This Study

Schmidt et al. (2025) studied this question.

synapsesocial.com/papers/68f6379bb481a140a36cf632https://doi.org/10.48550/arxiv.2506.15041
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Can LLMs Learn Macroeconomic Narratives from Social Media?2024
  2. 2EconNLI: Evaluating Large Language Models on Economics Reasoning2024
  3. 3The Role of AI in Economic Empirical Analysis: Focus on Large Language Models in Computational Economics2025
  4. 4Large language models for unstructured economic data processing: Enhancing GDP forecasting accuracy with heterogeneous textual information2026
  5. 5Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT2024 · 2 citations