CrudeBERT: Applying Economic Theory Towards Fine-Tuning Transformer-Based Sentiment Analysis Models to the Crude Oil Market

Himmet Kaplan, Ralf-Peter Mundani, Heiko Rölke, Albert Weichselbraun

2023

Abstract

Predicting market movements based on the sentiment of news media has a long tradition in data analysis. With advances in natural language processing, transformer architectures have emerged that enable contextually aware sentiment classification. Nevertheless, current methods built for the general financial market such as FinBERT cannot distinguish asset-specific value-driving factors. This paper addresses this shortcoming by presenting a method that identifies and classifies events that impact supply and demand in the crude oil markets within a large corpus of relevant news headlines. We then introduce CrudeBERT, a new sentiment analysis model that draws upon these events to contextualize and fine-tune FinBERT, thereby yielding improved sentiment classifications for headlines related to the crude oil futures market. An extensive evaluation demonstrates that CrudeBERT outperforms proprietary and open-source solutions in the domain of crude oil.

Paper Citation

in Harvard Style

Kaplan H., Mundani R., Rölke H. and Weichselbraun A. (2023). CrudeBERT: Applying Economic Theory Towards Fine-Tuning Transformer-Based Sentiment Analysis Models to the Crude Oil Market. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 324-334. DOI: 10.5220/0011749600003467

in Bibtex Style

@conference{iceis23,
author={Himmet Kaplan and Ralf-Peter Mundani and Heiko Rölke and Albert Weichselbraun},
title={CrudeBERT: Applying Economic Theory Towards Fine-Tuning Transformer-Based Sentiment Analysis Models to the Crude Oil Market},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={324-334},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011749600003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - CrudeBERT: Applying Economic Theory Towards Fine-Tuning Transformer-Based Sentiment Analysis Models to the Crude Oil Market
SN - 978-989-758-648-4
AU - Kaplan H.
AU - Mundani R.
AU - Rölke H.
AU - Weichselbraun A.
PY - 2023
SP - 324
EP - 334
DO - 10.5220/0011749600003467
PB - SciTePress