A Hybrid Deep Learning Framework for Stock Price Prediction Considering the Investor Sentiment of Online Forum Enhanced by Popularity
This work addresses the problem of stock price forecasting for financial analysts and investors, but it is incremental as it builds on existing deep learning and sentiment analysis methods.
The authors tackled stock price prediction by developing a hybrid deep learning framework that incorporates investor sentiment from online forums, enhanced by popularity, and technical indicators, achieving effective prediction results in experiments on four Chinese stocks.
Stock price prediction has always been a difficult task for forecasters. Using cutting-edge deep learning techniques, stock price prediction based on investor sentiment extracted from online forums has become feasible. We propose a novel hybrid deep learning framework for predicting stock prices. The framework leverages the XLNET model to analyze the sentiment conveyed in user posts on online forums, combines these sentiments with the post popularity factor to compute daily group sentiments, and integrates this information with stock technical indicators into an improved BiLSTM-highway model for stock price prediction. Through a series of comparative experiments involving four stocks on the Chinese stock market, it is demonstrated that the hybrid framework effectively predicts stock prices. This study reveals the necessity of analyzing investors' textual views for stock price prediction.