BondBERT: What we learn when assigning sentiment in the bond market

TL;DR

BondBERT is a specialized transformer model trained on bond-specific news that improves sentiment analysis and bond return forecasting, outperforming general financial models in capturing fixed income market dynamics.

Contribution

This paper introduces BondBERT, a domain-specific transformer model for bond market sentiment analysis, and presents a framework for adapting NLP models to low-volatility, domain-inverse tasks.

Findings

BondBERT shows positive correlation with bond returns.

It outperforms FinBERT, FinGPT, and Instruct-FinGPT in alignment and forecasting accuracy.

The framework effectively adapts transformers to bond-specific sentiment tasks.

Abstract

Bond markets respond differently to macroeconomic news compared to equity markets, yet most sentiment models are trained primarily on general financial or equity news data. However, bond prices often move in the opposite direction to economic optimism, making general or equity-based sentiment tools potentially misleading. We introduce BondBERT, a transformer-based language model fine-tuned on bond-specific news. BondBERT can act as the perception and reasoning component of a financial decision-support agent, providing sentiment signals that integrate with forecasting models. We propose a generalisable framework for adapting transformers to low-volatility, domain-inverse sentiment tasks by compiling and cleaning 30,000 UK bond market articles (2018-2025). BondBERT's sentiment predictions are compared against FinBERT, FinGPT, and Instruct-FinGPT using event-based correlation, up/down accuracy analyses, and LSTM forecasting across ten UK sovereign bonds. We find that BondBERT consistently produces positive correlations with bond returns, and achieves higher alignment and forecasting accuracy than the three baseline models. These results demonstrate that domain-specific sentiment adaptation better captures fixed income dynamics, bridging a gap between NLP advances and bond market analytics.