Integrating the sentiments of multiple news providers for stock market index movement prediction: A deep learning approach based on evidential reasoning rule

In this study, we investigate the predictive capabilities of different news providers based on sentiment analysis, and propose a framework that endows different weights to different news providers for improving the prediction performance. In sentiment analysis, the prevalent Loughran-McDonald sentiment dictionary is utilized to calculate the sentiment scores of news articles, and the sentiment index of each news provider is obtained by inte-grating these sentiment scores. Based on the market data and sentiment indices of multiple news providers, we employ the recurrent neural network to build a number of base clas-sifiers, and adopt the evidential reasoning rule to combine these base classifiers for predict-ing the stock market index movement. Additionally, the genetic algorithm is used to optimize the weights of base classifiers and important hyper-parameters of the recurrent neural network. In the experimental study, we apply the proposed approach to the daily movement prediction of the S&P 500 index, Dow Jones Industrial Average index and NASDAQ 100 index, and compare it with some state-of-the-art methods. The results show that our approach is effective for improving the prediction performance. Besides, the designed trading strategy based on the results of the proposed model achieves higher return rates than other trading strategies.(c) 2022 Elsevier Inc. All rights reserved.

Automated summary

This study investigates the predictive abilities of different news providers based on sentiment analysis and proposes a framework that assigns different weights to improve prediction performance. The Loughran-McDonald sentiment dictionary is used for sentiment analysis, and the sentiment scores are integrated to obtain the sentiment index of each news provider. Recurrent neural networks are employed to build base classifiers, and the evidential reasoning rule is adopted to combine them for predicting stock market index movement. The genetic algorithm is used to optimize the weights of base classifiers and important hyper-parameters. Experimental results demonstrate the effectiveness of the proposed approach in improving prediction performance, and the trading strategy based on the model's results achieves higher return rates.