An empirical study of the relationship between investor sentiment and stock market performance based on support vector machine modeling

Abstract

This study explores the impact of investor sentiment on stock market performance and empirically analyzes the value of its application in market prediction by constructing a sentiment classification system using Support Vector Machine (SVM) model. By collecting market-related text data, extracting investor sentiment features using text sentiment analysis, and combining them with stock market data, a machine learning-based prediction model is constructed. The experimental results show that investor sentiment has a significant impact on the volatility of the stock market, and the support vector machine model shows high accuracy and applicability in sentiment classification and market prediction. Compared with traditional sentiment analysis methods, the machine learning method used in this study can capture the impact of sentiment fluctuations on market movements more effectively, providing a new technical means for financial market sentiment analysis. The research results can provide investors with a more refined basis for market judgment, and can also serve as a reference for financial regulators to formulate risk warning strategies. Future research can further optimize the sentiment analysis model, improve the real-time data processing, and explore multimodal data integration to enhance the accuracy and stability of market sentiment prediction.