AUTHOR=Lee Chi-Yuan , Anderl Eva TITLE=Does business news sentiment matter in the energy stock market? Adopting sentiment analysis for short-term stock market prediction in the energy industry JOURNAL=Frontiers in Artificial Intelligence VOLUME=Volume 8 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1559900 DOI=10.3389/frai.2025.1559900 ISSN=2624-8212 ABSTRACT=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.