BRIEF RESEARCH REPORT article
Front. Artif. Intell.
Sec. AI in Finance
Volume 8 - 2025 | doi: 10.3389/frai.2025.1559900
This article is part of the Research TopicApplications of AI and Machine Learning in Finance and EconomicsView all 10 articles
Does business news sentiment matter in the energy stock market? Adopting sentiment analysis for short-term stock market prediction in the energy industry
Provisionally accepted- Munich University of Applied Sciences, Munich, Germany
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Characterized by high volatility the energy stock market provides ample research potential for stock market prediction using machine learning models. This paper investigates using business news as an indicator of market sentiment in Recurrent Neural Networks. The authors adopt a finance-specific Transformer-based model, FinBERT, for news sentiment analysis and use a Long Short-Term Memory (LSTM) model for stock prediction. As prior research indicates that sentiment may vary for different news elements, they specifically explore differences between news headlines and content. Results show that (1) Transformer-based sentiment analysis of business news can improve stock market prediction in the energy industry and that (2) sentiment of news content is more effective than sentiment of news headlines.
Keywords: energy industry, Stock prediction, sentiment analysis, News sentiment, LSTM, FinBERT
Received: 13 Jan 2025; Accepted: 10 Jul 2025.
Copyright: © 2025 Lee and Anderl. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Eva Anderl, Munich University of Applied Sciences, Munich, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.