Construction of Investor Sentiment Index and Its Application in Investment Decision-Making

In recent years, research on the construction and application of investor sentiment indexes has become an important research direction in fields such as behavioral finance and asset pricing. With the development of emerging technologies such as big data, artificial intelligence, and cloud computing, the quantitative methods of investor sentiment indexes have been rapidly improved. However, the current construction of the investor sentiment index still faces the problems of model overfitting and data bias under high-frequency data, combining text analysis with multi-modal sentiment recognition to improve robustness, and its application in risk management, timing strategies, and stability monitoring. This review reconstructs the indicator framework by integrating multi-source heterogeneous data and adopting methods such as nonlinear causal tests to improve its effectiveness in cross-regional applications. The improved investor sentiment index construction method can more accurately reflect changes in market sentiment, provide important theoretical significance and practical value for the in-depth revelation of the key mechanism of investor behavior and market fluctuations, and effectively develop risk early warning tools.