Financial sentiment analysis using FinBERT with application in predicting stock movement

TL;DR

This paper presents an advanced deep learning approach combining FinBERT sentiment analysis with LSTM networks to improve stock market trend prediction accuracy, outperforming traditional models.

Contribution

It introduces a novel integration of FinBERT-based sentiment analysis with LSTM for financial forecasting, along with optimization techniques to enhance predictive performance.

Findings

Sentiment analysis improves market trend prediction accuracy.

The combined FinBERT-LSTM model outperforms standard BERT, LSTM, and ARIMA.

Optimization techniques further enhance model robustness.

Abstract

In this study, we integrate sentiment analysis within a financial framework by leveraging FinBERT, a fine-tuned BERT model specialized for financial text, to construct an advanced deep learning model based on Long Short-Term Memory (LSTM) networks. Our objective is to forecast financial market trends with greater accuracy. To evaluate our model's predictive capabilities, we apply it to a comprehensive dataset of stock market news and perform a comparative analysis against standard BERT, standalone LSTM, and the traditional ARIMA models. Our findings indicate that incorporating sentiment analysis significantly enhances the model's ability to anticipate market fluctuations. Furthermore, we propose a suite of optimization techniques aimed at refining the model's performance, paving the way for more robust and reliable market prediction tools in the field of AI-driven finance.