融合社交情感分析的股市预测探究
|
摘要
针对现有股市预测研究中所存在的大众情感度量不够全面的问题,提出了一种基于社交情感分析的股市预测模型.该模型首先基于异构图模型的证券情感量化方法对社交媒介的数据进行情感分析,得到量化的情感时间序列;然后,基于自组织神经网络模型对情感序列及行情指数序列进行建模,从而对股票指数进行预测.在国内社交媒介及股市行情数据集上的实验结果表明,本文所建立的模型在预测误差和精度上较BP(Back Propagation)神经网络分别提升了15%和12%,能更好地预测股票指数.
Considering the public sentiment is not comprehensively measured in the existing stock market prediction study, the study proposes a stock market prediction model using social sentiment analysis. First of all, a securities sentiment quantitative method based on heterogeneous graph model is applied for sentiment analysis on social media data,and thus quantified sentiment time sequence is obtained. Secondly, a prediction model based on self-organizing neural network is proposed for the stock index prediction by using sentiment sequence and the quotation index sequence. The experimental results on the domestic stock market and social media data sets show that the proposed model has improved by 15% and 12% over the BP(Back Propagation) neural network in the prediction error and accuracy respectively, which can better predict the stock market.
Considering the public sentiment is not comprehensively measured in the existing stock market prediction study, the study proposes a stock market prediction model using social sentiment analysis. First of all, a securities sentiment quantitative method based on heterogeneous graph model is applied for sentiment analysis on social media data,and thus quantified sentiment time sequence is obtained. Secondly, a prediction model based on self-organizing neural network is proposed for the stock index prediction by using sentiment sequence and the quotation index sequence. The experimental results on the domestic stock market and social media data sets show that the proposed model has improved by 15% and 12% over the BP(Back Propagation) neural network in the prediction error and accuracy respectively, which can better predict the stock market.
引文
1 Bollen J,Mao HN,Zeng XJ.Twitter mood predicts the stock market.Journal of Computational Science,2011,2(1):1-8.[doi:10.1016/j.jocs.2010.12.007]
2魏巍贤,周晓明.中国股票市场波动的非线性GARCH预测模型.预测,1999,(5):47-49.
3赵华,蔡建文.基于MRS-GARCH模型的中国股市波动率估计与预测.数理统计与管理,2011,30(5):912-921.
4杨继平,袁璐,张春会.基于结构转换非参数GARCH模型的VaR估计.管理科学学报,2014,17(2):69-80.
5曾慧.ARCH模型对上证指数收益波动性的实证研究.统计与决策,2005,(6):97-98.
6 Yu J.Forecasting volatility in the New Zealand stock market.Applied Financial Economics,2002,12(3):193-202.[doi:10.1080/09603100110090118]
7 Durham GB.SV mixture models with application to S&P500 index returns.Journal of Financial Economics,2007,85(3):822-856.[doi:10.1016/j.jfineco.2006.06.005]
8杨克磊,毛明来,徐正国.随机波动模型的沪深股市比较研究.天津大学学报(社会科学版),2004,6(4):334-338.
9周彦,张世英.基于MCMC方法的连续时间SV模型建模研究.工业工程,2007,10(1):83-86.
10梁艳,徐元华.基于不对称SV模型的隔夜信息对股市影响研究.大连理工大学学报(社会科学版),2011,32(3):34-38.
11 Cortes C,Vapnik V.Support-vector networks.Machine Learning,1995,20(3):273-297.
12 Pai PF,Lin CS.A hybrid ARIMA and support vector machines model in stock price forecasting.Omega,2005,33(6):497-505.[doi:10.1016/j.omega.2004.07.024]
13杨耀宇.基于支持向量机的沪深300指数预测研究[硕士学位论文].上海:上海师范大学,2014.
14李坤,谭梦羽.基于小波支持向量机回归的股票预测.统计与决策,2014,(6):32-36.
15陈懿冰,张玲玲,聂广礼,等.基于改进的支持向量回归机的金融时序预测.数学的实践与认识,2012,42(4):38-44.
16王上飞,周佩玲,吴耿峰,等.径向基神经网络在股市预测中的应用.预测,1998,(6):44-46.
17杜爱玲,武敬.神经网络在股市预测中的应用一—基于BP,RBF与GRNN.经营管理者,2014,(11):394.
18杨帆.基于遗传神经网络算法的股票预测研究[硕士学位论文].兰州:兰州大学,2013.
19李聪.基于BP神经网络的股票指数期货价格预测[硕士学位论文].青岛:青岛大学,2012.
20马东宇.基于Gaussian型RBF神经网络的函数逼近与应用[硕士学位论文].长沙:中南大学,2011.
21 Gilbert E,Karahalios K.Widespread worry and the stock market.Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media.Washington,DC,USA.2010.58-65.
22 Liao XW,Chen H,Wei JJ,et al.A weighted lexicon-based generative model for opinion retrieval.2014 International Conference on Machine Learning and Cybernetics(ICMLC).Lanzhou,China.2014.821-826.
2魏巍贤,周晓明.中国股票市场波动的非线性GARCH预测模型.预测,1999,(5):47-49.
3赵华,蔡建文.基于MRS-GARCH模型的中国股市波动率估计与预测.数理统计与管理,2011,30(5):912-921.
4杨继平,袁璐,张春会.基于结构转换非参数GARCH模型的VaR估计.管理科学学报,2014,17(2):69-80.
5曾慧.ARCH模型对上证指数收益波动性的实证研究.统计与决策,2005,(6):97-98.
6 Yu J.Forecasting volatility in the New Zealand stock market.Applied Financial Economics,2002,12(3):193-202.[doi:10.1080/09603100110090118]
7 Durham GB.SV mixture models with application to S&P500 index returns.Journal of Financial Economics,2007,85(3):822-856.[doi:10.1016/j.jfineco.2006.06.005]
8杨克磊,毛明来,徐正国.随机波动模型的沪深股市比较研究.天津大学学报(社会科学版),2004,6(4):334-338.
9周彦,张世英.基于MCMC方法的连续时间SV模型建模研究.工业工程,2007,10(1):83-86.
10梁艳,徐元华.基于不对称SV模型的隔夜信息对股市影响研究.大连理工大学学报(社会科学版),2011,32(3):34-38.
11 Cortes C,Vapnik V.Support-vector networks.Machine Learning,1995,20(3):273-297.
12 Pai PF,Lin CS.A hybrid ARIMA and support vector machines model in stock price forecasting.Omega,2005,33(6):497-505.[doi:10.1016/j.omega.2004.07.024]
13杨耀宇.基于支持向量机的沪深300指数预测研究[硕士学位论文].上海:上海师范大学,2014.
14李坤,谭梦羽.基于小波支持向量机回归的股票预测.统计与决策,2014,(6):32-36.
15陈懿冰,张玲玲,聂广礼,等.基于改进的支持向量回归机的金融时序预测.数学的实践与认识,2012,42(4):38-44.
16王上飞,周佩玲,吴耿峰,等.径向基神经网络在股市预测中的应用.预测,1998,(6):44-46.
17杜爱玲,武敬.神经网络在股市预测中的应用一—基于BP,RBF与GRNN.经营管理者,2014,(11):394.
18杨帆.基于遗传神经网络算法的股票预测研究[硕士学位论文].兰州:兰州大学,2013.
19李聪.基于BP神经网络的股票指数期货价格预测[硕士学位论文].青岛:青岛大学,2012.
20马东宇.基于Gaussian型RBF神经网络的函数逼近与应用[硕士学位论文].长沙:中南大学,2011.
21 Gilbert E,Karahalios K.Widespread worry and the stock market.Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media.Washington,DC,USA.2010.58-65.
22 Liao XW,Chen H,Wei JJ,et al.A weighted lexicon-based generative model for opinion retrieval.2014 International Conference on Machine Learning and Cybernetics(ICMLC).Lanzhou,China.2014.821-826.