---
title: Measuring sentiment news with transformer-based language models
url: https://www.ml-quant.com/papers/repec/ecb-ecbwps-20263283/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-16
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:ecb:ecbwps:20263283
source_url: https://econpapers.repec.org/RePEc:ecb:ecbwps:20263283
featured: 2026-10-16
citations: unknown
topic: LLMs & Text
---


# Measuring sentiment news with transformer-based language models

FinBERT-based sentiment measures agree more closely with human raters than dictionary methods and better distinguish positive, neutral, and negative financial news articles.

- Source: https://econpapers.repec.org/RePEc:ecb:ecbwps:20263283
- Identifier: RePEc:ecb:ecbwps:20263283
- Released: 2026-10-09
- First featured: Quant Letter No. 135 (2026-10-16): https://www.ml-quant.com/issues/2026-10-16/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: LLMs & Text
- Authors: Borgioli, Stefano, Gallo, Giampiero M., Ongari, Chiara, Mavillonio, Maria Saveria, Giannetti, Caterina

## Related

- [From News to Returns: A Granger-Causal Hypergraph Transformer on the Sphere](https://www.ml-quant.com/papers/arxiv/2510.04357/): The research suggests the CSHT, a new architecture for financial time-series forecasting that considers the impact of financial news and sentiment on asset returns, providing robust generalisation across market regimes and clear attribution pathways.
- [Visualizing Public Opinion on X: A Real-Time Sentiment Dashboard Using VADER and DistilBERT](https://www.ml-quant.com/papers/arxiv/2504.15448/): A sentiment analysis system, using Natural Language Processing and machine learning, offers real-time interpretation of public opinion towards corporations, highlighting disparities in public sentiment and assisting stakeholders in strategic decision-making.
- [Advanced Deep Learning Techniques for Analyzing Earnings Call Transcripts: Methodologies and Applications](https://www.ml-quant.com/papers/arxiv/2503.01886/): The paper compares the effectiveness of deep learning methods like BERT, FinBERT, and ULMFiT in sentiment analysis of financial transcripts, offering insights for practical financial decision-making.
- [A Systematic Literature Review on Sentimental Analysis using Machine Learning for Preprocessing, Feature Extraction and Classification](https://www.ml-quant.com/papers/ssrn/5061012/): The study reviews sentiment analysis methods in Natural Language Processing, covering data collection, preprocessing, feature extraction, and classification.
- [No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations](https://www.ml-quant.com/papers/arxiv/2407.10964/): The FUNGI method improves transformer encoders' features using self-supervised gradients, enhancing performance in vision, natural language processing, and audio tasks and datasets.
- [SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists](https://www.ml-quant.com/papers/arxiv/2408.17437/): SYNTHEVAL is a testing framework that uses large language models to generate tests for evaluating NLP models, particularly in sentiment analysis and toxic language detection.