基于Bert股吧舆情分析的特征融合股价走势预测研究  

Feature Fusion for Stock Price Trend Prediction Based on Bert Stock Forum Opinion Analysis

作　　者：李梦[1] 黄政祺 LI Meng;HUANG Zhengqi(School of Mathematics and Statistics,Chongqing Technology and Business University,Chongqing 400067,China;Chongqing Key Laboratory of Economic and Social Applied Statistics,Chongqing Technology and Business University,Chongqing 400067,China)

机构地区：[1]重庆工商大学数学与统计学院,重庆400067 [2]重庆工商大学经济社会应用统计重庆市重点实验室,重庆400067

出　　处：《重庆工商大学学报（自然科学版）》2023年第4期77-86,共10页Journal of Chongqing Technology and Business University:Natural Science Edition

基　　金：重庆市科学技术委员会自然科学基金计划资助项目(CSTC2020JCYJ-MSXMX0162).

摘　　要：传统股价预测模型往往只考虑时序性数据且局限于模型自身机制,而忽略舆情对股价的影响,导致预测精度不高,针对该问题,提出基于Bert股吧舆情分析的特征融合预测模型对股价收盘价进行涨跌幅预测。首先,采用Bert自然语言处理对股吧舆情以及公司公告政策进行情感分类,并转化为虚拟变量,构建金融舆情情感特征库;然后将金融舆情特征库和时序性数据合并构建特征融合矩阵;最后输入长短期记忆网络模型(LSTM)进行股价收盘价预测,并得出股价的涨跌结果。以华银电力(600744.SH)为例进行实证分析,实验结果表明:引入股票情感特征后的模型,得到的股价走势准确率上升了8.63%,预测收盘价的回归指标F_(MAPE)、F_(RMSE)分别下降了23.59%、22.9%,R^(2)提高了8.11%,证明引入新的舆情情感特征在实际预测中能提高股价预测的准确率,可以作为精准预测股价走势的手段。Traditional stock price forecasting models often only consider time-series data and are limited to the model’s own mechanism,ignoring the impact of public opinion on stock prices,resulting in poor forecasting accuracy.To solve this problem,a feature fusion prediction model based on Bert stock forum public opinion analysis was proposed to predict the trend of stock price.Firstly,Bert natural language processing was used to classify the sentiment of stock forum opinions and company’s announcement policies,and the emotion after classification was converted into virtual variables to construct the emotion feature database of financial public opinions.Then,the feature fusion matrix was constructed by merging the financial public opinion feature database and the time-series data.Finally,a long short-term memory(LSTM)network model was used to predict the closing price of the stock and to derive the upward and downward results of the stock price.Taking Huayin Power(600744.SH)as an example for empirical analysis,the experimental results showed that after the introduction of stock sentiment features into the model,the accuracy of the stock price trend increased by 8.63%,the regression indicators of F_(MAPE) and F_(RMSE) for predicting the closing price decreased by 23.59%and 22.9%,respectively,and R^(2) increased by 8.11%.This demonstrates that the introduction of new sentiment features of public opinion can improve the accuracy of stock price prediction in practical forecasting and can be used as a means to accurately predict the trend of stock price.

关 键 词：文本情感分析 股价预测 Bert自然语言处理模型 长短期记忆网络模型 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]