Can real-time investor sentiment help predict the high-frequency stock returns? Evidence from a mixed-frequency-rolling decomposition forecasting method

This research examines the predictive effect of real-time investor sentiment on high-frequency stock returns. Utilizing text sentiment analysis, we extract investor sentiment with a half-hour frequency from the stock message board. The RR-MIDAS method is used to model half-hourly sentiment and three-minute stock returns, and economic analysis reveals that investor sentiment significantly affects the stock returns during seven high-frequency periods, and the influence gradually weakens. Subsequently, we propose the "MF-EEMD-ML" prediction system, which introduces a rolling decomposition algorithm into the RR-MIDAS framework for predicting high-frequency trend items combined with real-time forum sentiment. The results, using rolling EMD decomposition for comparison, show that the "MF-EEMD-ML" system achieves a maximum reduction of 19.18 % in MAE, 19.08 % in RMSE, 11.71 % in SMAPE, and a maximum improvement of 16.66 % in DS. Additionally, the outcomes of the Diebold-Mariano (DM) tests also demonstrate that the "MF-EEMD-ML" prediction system significantly outperforms both the "MF-EMD-ML" system and the LR model.