Centralbankroberta Sentiment Classifier

🚀 CentralBankRoBERTa

A Fine-Tuned Large Language Model for Central Bank Communications

CentralBankRoBERTa is a large language model that combines an economic agent classifier, which can distinguish five basic macroeconomic agents, with a binary sentiment classifier to identify the emotional content of sentences in central bank communications.

🚀 Quick Start

Overview

The SentimentClassifier model can detect whether a given sentence is positive or negative for households, firms, the financial sector or the government. Based on the RoBERTa architecture, it has been fine-tuned on a diverse and extensive dataset to provide accurate predictions.

Intended Use

The SentimentClassifier model is designed for the analysis of central bank communications where sentiment analysis is crucial.

Performance

• Accuracy: 88%
• F1 Score: 0.88
• Precision: 0.88
• Recall: 0.88

✨ Features

• Combines an economic agent classifier and a binary sentiment classifier.
• Can distinguish five basic macroeconomic agents.
• Identifies the emotional content of sentences in central bank communications.

💻 Usage Examples

Basic Usage

from transformers import pipeline

# Load the SentimentClassifier model
sentiment_classifier = pipeline("text-classification", model="Moritz-Pfeifer/CentralBankRoBERTa-sentiment-classifier")

# Perform sentiment analysis
sentinement_result = sentiment_classifier("The early effects of our policy tightening are also becoming visible, especially in sectors like manufacturing and construction that are more sensitive to interest rate changes.")
print("Sentiment:", sentinement_result[0]['label'])

📚 Documentation

Citation

Please cite this model as Pfeifer, M. and Marohl, V.P. (2023) "CentralBankRoBERTa: A Fine-Tuned Large Language Model for Central Bank Communications". Journal of Finance and Data Science

Authors' Information

BibTeX entry and citation info

@article{Pfeifer2023,
  title = {CentralBankRoBERTa: A fine-tuned large language model for central bank communications},
  journal = {The Journal of Finance and Data Science},
  volume = {9},
  pages = {100114},
  year = {2023},
  issn = {2405-9188},
  doi = {https://doi.org/10.1016/j.jfds.2023.100114},
  url = {https://www.sciencedirect.com/science/article/pii/S2405918823000302},
  author = {Moritz Pfeifer and Vincent P. Marohl},
}

📄 License

This project is licensed under the MIT license.