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

Barter, Toby, Gao, Zheng, Christodoulaki, Eva, Chen, Maggie ORCID: https://orcid.org/0000-0001-7135-2116 and Cartlidge, John 2026. BondBERT: What we learn when assigning sentiment in the bond market. Presented at: 18th International Conference on Agents and Artificial Intelligence, Marbella, Spain, 5-8 March 2026. Published in: Rocha, A. P., Wahde, M. and Jaap van den Herik, H. eds. Proceedings of the 18th International Conference on Agents and Artificial Intelligence. , vol.5 SCITEPRESS - Science and Technology Publications, pp. 4056-4063. 10.5220/0014251100004052

Full text not available from this repository.

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 consistent ly 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.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Mathematics
Publisher:	SCITEPRESS - Science and Technology Publications
ISBN:	9789897587962
ISSN:	2184-433X
Last Modified:	07 Apr 2026 10:15
URI:	https://orca.cardiff.ac.uk/id/eprint/186188

Actions (repository staff only)

Edit Item