Financial Sentiment Analysis and Classification: A Comparative Study of Fine-Tuned Deep Learning Models

Dimitrios K. Nasiopoulos (), Konstantinos I. Roumeliotis (), Damianos P. Sakas, Kanellos Toudas and Panagiotis Reklitis
Additional contact information
Dimitrios K. Nasiopoulos: Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, 11855 Athens, Greece
Konstantinos I. Roumeliotis: Department of Informatics and Telecommunications, University of the Peloponnese, 22131 Tripoli, Greece
Damianos P. Sakas: Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, 11855 Athens, Greece
Kanellos Toudas: Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, 11855 Athens, Greece
Panagiotis Reklitis: Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, 11855 Athens, Greece

IJFS, 2025, vol. 13, issue 2, 1-27

Abstract: Financial sentiment analysis is crucial for making informed decisions in the financial markets, as it helps predict trends, guide investments, and assess economic conditions. Traditional methods for financial sentiment classification, such as Support Vector Machines (SVM), Random Forests, and Logistic Regression, served as our baseline models. While somewhat effective, these conventional approaches often struggled to capture the complexity and nuance of financial language. Recent advancements in deep learning, particularly transformer-based models like GPT and BERT, have significantly enhanced sentiment analysis by capturing intricate linguistic patterns. In this study, we explore the application of deep learning for financial sentiment analysis, focusing on fine-tuning GPT-4o, GPT-4o-mini, BERT, and FinBERT, alongside comparisons with traditional models. To ensure optimal configurations, we performed hyperparameter tuning using Bayesian optimization across 100 trials. Using a combined dataset of FiQA and Financial PhraseBank, we first apply zero-shot classification and then fine tune each model to improve performance. The results demonstrate substantial improvements in sentiment prediction accuracy post-fine-tuning, with GPT-4o-mini showing strong efficiency and performance. Our findings highlight the potential of deep learning models, particularly GPT models, in advancing financial sentiment classification, offering valuable insights for investors and financial analysts seeking to understand market sentiment and make data-driven decisions.

Keywords: financial sentiment analysis; decision support systems; machine learning; financial sentiment classification; deep learning; natural language processing; transformer models; BERT model; GPT model; market prediction (search for similar items in EconPapers)
JEL-codes: F2 F3 F41 F42 G1 G2 G3 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7072/13/2/75/pdf (application/pdf)
https://www.mdpi.com/2227-7072/13/2/75/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijfss:v:13:y:2025:i:2:p:75-:d:1648129

Access Statistics for this article

IJFS is currently edited by Ms. Hannah Lu

More articles in IJFS from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().