基于时间窗口的舆情异动量化模型
|
摘要
现有互联网文本舆情分析模型多数未考虑时间因素的影响,对舆情动态变化过程缺乏定量刻画,难以准确发现舆情演化的动态过程和关键要素。为此,提出一种改进的舆情异动量化模型。通过线性回归模型得出不同时间窗口内的舆情静态表现,利用趋势线刻画舆情随时间的变化情况,结合舆情整体走势和异动角度获得舆情异动指数。基于国内A股涨跌预测的实验结果表明,与传统舆情分析模型相比,该模型具有更高的预测准确率和更好的稳定性。
Most of the existing Internet text public opinion analysis models do not consider the influence of time factors,and lack of quantitative description of the dynamic change process of public opinion,so it is difficult to accurately discover the dynamic process and key elements of public opinion evolution.Therefore,this paper proposes an improved quantitative model of public opinions change.Through the linear regression model,the static performance of the opinion in different time windows is obtained.The trend line is used to describe the change situation of the public opinion over time,and the public opinions change index is obtained by combining the overall trend and the change angle of the public opinion.Based on the fluctuated forecast of the domestic A-share stocks,experimental results show that the model has a higher prediction accuracy and stability than the traditional public opinion analysis model.
Most of the existing Internet text public opinion analysis models do not consider the influence of time factors,and lack of quantitative description of the dynamic change process of public opinion,so it is difficult to accurately discover the dynamic process and key elements of public opinion evolution.Therefore,this paper proposes an improved quantitative model of public opinions change.Through the linear regression model,the static performance of the opinion in different time windows is obtained.The trend line is used to describe the change situation of the public opinion over time,and the public opinions change index is obtained by combining the overall trend and the change angle of the public opinion.Based on the fluctuated forecast of the domestic A-share stocks,experimental results show that the model has a higher prediction accuracy and stability than the traditional public opinion analysis model.
引文
[1] WEI G,ZHANG W,ZHOU L.Stock trends prediction combining the public opinion analysis[C]//Proceedings of International Conference on Logistics,Informatics and Service Sciences.Washington D.C.,USA: IEEE Press,2016:1-6.
[2] BOLLEN J,MAO H,ZENG X.Twitter mood predicts the stock market[J].Journal of Computational Science,2010,2(1):1-8.
[3] FU T,LEE K,SZE D,et al.Discovering the correlation between stock time series and financial news[C]//Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Washington D.C.,USA:IEEE Press,2009:880-883.
[4] 张成功,刘培玉,朱振方,等.一种基于极性词典的情感分析方法[J].山东大学学报(理学版),2012,47(3):50-53.
[5] 肖江,丁星,何荣杰.基于领域情感词典的中文微博情感分析[J].电子设计工程,2015,23(12):18-21.
[6] TURNEY P D.Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Philadelphia,USA:ACL Press,2002:417-424.
[7] 朱嫣岚,闵锦,周雅倩,等.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[8] 秦锋,王恒,郑啸,等.基于上下文语境的微博情感分析[J].计算机工程,2017,43(3):241-246.
[9] 梁军,柴玉梅,原慧斌,等.基于深度学习的微博情感分析[J].中文信息学报,2014,28(5):155-161.
[10] 陈钊,徐睿峰,桂林,等.结合卷积神经网络和词语情感序列特征的中文情感分析[J].中文信息学报,2015,29(6):172-178.
[11] PANG B,LEE L.Opinion mining and sentiment analysis[M]//LIU B.Web data mining.Berlin,Germany:Springer,2008:459-526.
[12] 李爱萍,邸鹏,段利国.基于句子情感加权算法的篇章情感分析[J].小型微型计算机系统,2015,36(10):2252-2256.
[13] 李本阳,关毅,董喜双,等.基于单层标注级联模型的篇章情感倾向分析[J].中文信息学报,2012,26(4):3-8.
[14] 桂斌,杨小平,朱建林,等.基于意群划分的中文微博情感倾向分析研究[J].中文信息学报,2015,29(3):100-105.
[15] 李寿山,黄居仁.基于Stacking组合分类方法的中文情感分类研究[J].中文信息学报,2010,24(5):56-61.
[16] ASUR S,HUBERMAN B A.Predicting the future with social media[C]//Proceedings of 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Washington D.C.,USA:IEEE Press,2010:492-499.
[17] GRUHL D,GUHA R,KUMAR R,et al.The predictive power of online chatter[C]//Proceeding of the 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining.New York,USA:ACM Press,2005:78-87.
[18] SCHUMAKER R P,CHEN H.Textual analysis of stock market prediction using breaking financial news[J].ACM Transactions on Information Systems,2009,27(2):1-19.
[19] PRECHTER R R,PARKER W D.The financial/economic dichotomy in social behavioral dynamics: the socionomic perspective[J].Journal of Behavioral Finance,2007,8(2):84-108.
[20] PRECHTER R J.The wave principle of human social behavior and the new science of socionomics[M].[S.l.]:New Classics Press,2002.
[21] SMITH V L.Constructivist and ecological rationality in economics[J].American Economic Review,2003,93(3):465-508.
[22] NOFSINGER J R.Social mood and financial economics[J].Journal of Behaviour Finance,2005,6(3): 144-160.
[23] BUTLER K C,MALAIKAH S J.Efficiency and inefficiency in thinly traded stock markets[J].Journal of Banking and Finance,1992,16(1):197-210.
[24] QIAN B,RASHEED K.Stock market prediction with multiple classifiers[J].Applied Intelligence,2007,26(1):25-33.
[25] WANG J,LEU J.Stock market trend prediction using ARIMA-based neural networks[C]//Proceedings of International Conference on Neural Networks.Washington D.C.,USA:IEEE Press,1996:2160-2165.
[26] KIM K.Financial time series forecasting using support vector machines[J].Neurocomputing,2003,55(3):307-319.
[27] CHEN R,MARIUS L.Sentiment analysis of twitter feeds for the prediction of stock market movement[EB/OL].[2017-12-11].https://www.researchgate.net/publication/290812225_Sentiment_analysis_of_Twitter_feeds_for_the_prediction_of_stock_market_movement.
[28] ZHAI Y,HSU A,HALGAMUGE S K.Combining news and technical indicators in daily stock price trends prediction[C]//Proceedings of International Symposium on Neural Networks.Berlin,Germany:Springer,2007:1087-1096.
[29] MITTAL A,ARPIT G.Stock prediction using twitter sentiment analysis[EB/OL].[2017-12-11].http://cs229.stanford.edu/proj2011/Goel Mittal-Stock Market Prediction Using Twitter Sentiment Analysis.pdf.
[30] CAKRA Y E,TRISEDYA B D.Stock price prediction using linear regression based on sentiment analysis[C]//Proceedings of International Conference on Advanced Computer Science and Information Systems.Washington D.C.,USA: IEEE Press,2015:147-154.
[31] ZHANG X.Predicting stock market indicators through Twitter “I hope it is not as bad as I fear”[J].Procedia Social and Behavioral Sciences,2011,26: 55-62.
[32] 黄挺,姬东鸿.基于图模型和多分类器的微博情感倾向性分析[J].计算机工程,2015,41(4):171-175.
[33] LE T N,WU P,CHAN W,et al.Predicting collective sentiment dynamics from time-series social media[C]//Proceedings of International Workshop on Issues of Sentiment Discovery and Opinion Mining.Washington D.C.,USA: IEEE Press,2012:1-8.
[34] ROSIN P.Techniques for assessing polygonal approximations of curves[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(6):659-666.
[2] BOLLEN J,MAO H,ZENG X.Twitter mood predicts the stock market[J].Journal of Computational Science,2010,2(1):1-8.
[3] FU T,LEE K,SZE D,et al.Discovering the correlation between stock time series and financial news[C]//Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Washington D.C.,USA:IEEE Press,2009:880-883.
[4] 张成功,刘培玉,朱振方,等.一种基于极性词典的情感分析方法[J].山东大学学报(理学版),2012,47(3):50-53.
[5] 肖江,丁星,何荣杰.基于领域情感词典的中文微博情感分析[J].电子设计工程,2015,23(12):18-21.
[6] TURNEY P D.Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Philadelphia,USA:ACL Press,2002:417-424.
[7] 朱嫣岚,闵锦,周雅倩,等.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[8] 秦锋,王恒,郑啸,等.基于上下文语境的微博情感分析[J].计算机工程,2017,43(3):241-246.
[9] 梁军,柴玉梅,原慧斌,等.基于深度学习的微博情感分析[J].中文信息学报,2014,28(5):155-161.
[10] 陈钊,徐睿峰,桂林,等.结合卷积神经网络和词语情感序列特征的中文情感分析[J].中文信息学报,2015,29(6):172-178.
[11] PANG B,LEE L.Opinion mining and sentiment analysis[M]//LIU B.Web data mining.Berlin,Germany:Springer,2008:459-526.
[12] 李爱萍,邸鹏,段利国.基于句子情感加权算法的篇章情感分析[J].小型微型计算机系统,2015,36(10):2252-2256.
[13] 李本阳,关毅,董喜双,等.基于单层标注级联模型的篇章情感倾向分析[J].中文信息学报,2012,26(4):3-8.
[14] 桂斌,杨小平,朱建林,等.基于意群划分的中文微博情感倾向分析研究[J].中文信息学报,2015,29(3):100-105.
[15] 李寿山,黄居仁.基于Stacking组合分类方法的中文情感分类研究[J].中文信息学报,2010,24(5):56-61.
[16] ASUR S,HUBERMAN B A.Predicting the future with social media[C]//Proceedings of 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.Washington D.C.,USA:IEEE Press,2010:492-499.
[17] GRUHL D,GUHA R,KUMAR R,et al.The predictive power of online chatter[C]//Proceeding of the 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining.New York,USA:ACM Press,2005:78-87.
[18] SCHUMAKER R P,CHEN H.Textual analysis of stock market prediction using breaking financial news[J].ACM Transactions on Information Systems,2009,27(2):1-19.
[19] PRECHTER R R,PARKER W D.The financial/economic dichotomy in social behavioral dynamics: the socionomic perspective[J].Journal of Behavioral Finance,2007,8(2):84-108.
[20] PRECHTER R J.The wave principle of human social behavior and the new science of socionomics[M].[S.l.]:New Classics Press,2002.
[21] SMITH V L.Constructivist and ecological rationality in economics[J].American Economic Review,2003,93(3):465-508.
[22] NOFSINGER J R.Social mood and financial economics[J].Journal of Behaviour Finance,2005,6(3): 144-160.
[23] BUTLER K C,MALAIKAH S J.Efficiency and inefficiency in thinly traded stock markets[J].Journal of Banking and Finance,1992,16(1):197-210.
[24] QIAN B,RASHEED K.Stock market prediction with multiple classifiers[J].Applied Intelligence,2007,26(1):25-33.
[25] WANG J,LEU J.Stock market trend prediction using ARIMA-based neural networks[C]//Proceedings of International Conference on Neural Networks.Washington D.C.,USA:IEEE Press,1996:2160-2165.
[26] KIM K.Financial time series forecasting using support vector machines[J].Neurocomputing,2003,55(3):307-319.
[27] CHEN R,MARIUS L.Sentiment analysis of twitter feeds for the prediction of stock market movement[EB/OL].[2017-12-11].https://www.researchgate.net/publication/290812225_Sentiment_analysis_of_Twitter_feeds_for_the_prediction_of_stock_market_movement.
[28] ZHAI Y,HSU A,HALGAMUGE S K.Combining news and technical indicators in daily stock price trends prediction[C]//Proceedings of International Symposium on Neural Networks.Berlin,Germany:Springer,2007:1087-1096.
[29] MITTAL A,ARPIT G.Stock prediction using twitter sentiment analysis[EB/OL].[2017-12-11].http://cs229.stanford.edu/proj2011/Goel Mittal-Stock Market Prediction Using Twitter Sentiment Analysis.pdf.
[30] CAKRA Y E,TRISEDYA B D.Stock price prediction using linear regression based on sentiment analysis[C]//Proceedings of International Conference on Advanced Computer Science and Information Systems.Washington D.C.,USA: IEEE Press,2015:147-154.
[31] ZHANG X.Predicting stock market indicators through Twitter “I hope it is not as bad as I fear”[J].Procedia Social and Behavioral Sciences,2011,26: 55-62.
[32] 黄挺,姬东鸿.基于图模型和多分类器的微博情感倾向性分析[J].计算机工程,2015,41(4):171-175.
[33] LE T N,WU P,CHAN W,et al.Predicting collective sentiment dynamics from time-series social media[C]//Proceedings of International Workshop on Issues of Sentiment Discovery and Opinion Mining.Washington D.C.,USA: IEEE Press,2012:1-8.
[34] ROSIN P.Techniques for assessing polygonal approximations of curves[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(6):659-666.