Research on stock market sentiment analysis and prediction method based on convolutional neural network

This study proposes a deep learning-driven stock market sentiment analysis and prediction framework based on the fusion model of convolutional neural network (CNN) and long short-term memory network (LSTM). Natural language processing (NLP) technology is used to extract the sentiment features of financial news and social media texts, and a high-dimensional feature space is constructed by combining the market transaction data. CNN is responsible for local feature extraction, and LSTM is used for time-series modeling to realize the accurate prediction of market sentiment. Experimental results show that the model outperforms a single deep learning model in terms of mean square error (MSE), coefficient of determination (R2) and F1-score, which proves the effectiveness of the fusion method. The research results provide scientific support for financial market prediction and investment decision-making.