What does this research mean for the field?

A dual-stream deep learning framework that integrates wavelet-processed numerical price data with FinBERT-based news sentiment analysis using CNN-LSTM networks significantly improves stock price prediction accuracy. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This study aims to enhance stock price prediction accuracy by integrating numerical and textual data using deep learning.

June 1, 2026Open Access

Integrating sentiment analysis with CNN–LSTM models for stock price forecasting

Key Points

This study aims to enhance stock price prediction accuracy by integrating numerical and textual data using deep learning.
Developed a dual-stream deep learning framework combining wavelet-processed price data and FinBERT-based sentiment analysis.
Employed CNN–LSTM networks to model temporal dependencies across price data and news sentiment.
Conducted comprehensive evaluation to assess performance and accuracy.
Achieved test mean squared error (MSE) of 0.0220, indicating superior predictive performance.
Demonstrated significant improvement in forecasting accuracy through multimodal data integration.
Highlighted the dependence of performance on data quality and temporal alignment.

Abstract

Stock price prediction remains challenging due to markets’ non-linear, volatile nature. While existing studies analyse numerical data or textual news separately, their synergistic integration remains underexplored. We propose a novel dual-stream deep learning framework combining wavelet-processed price data with Financial Bidirectional Encoder Representations from Transformers (FinBERT)-based news sentiment analysis through intermediate feature fusion. Our architecture employs convolutional neural networks–long short-term memory (CNN–LSTM) networks to model cross-modal temporal dependencies. Comprehensive evaluation demonstrates superior performance (test mean squared error (MSE) = 0.0220), highlighting the value of multimodal integration for financial forecasting. Results suggest that this approach enhances predictive accuracy in algorithmic trading, though performance depends on data quality and temporal alignment between information sources.

Integrating sentiment analysis with CNN–LSTM models for stock price forecasting

Key Points

Abstract

Cite This Study

Also Consider

Also Consider