Boosting Financial Trend Prediction with Twitter Mood Based on Selective Hidden Markov Models

Financial trend prediction has been a hot topic in both academia and industry. This paper proposes to exploit Twitter mood to boost financial trend prediction based on selective hidden Markov models (sHMM). First, we expand the profile of mood states (POMS) Bipolar lexicon to extract rich society moods from massive tweets. Then, we determine which mood has the most predictive power on the financial index based on Granger causality analysis (GCA). Finally, we extend sHMM to combine financial index and the selected Twitter mood to predict next-day trend. Extensive experiments show that our method not only outperforms the state-of-the-art methods, but also provides controllability to financial trend prediction.

[1]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[2]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[3]  Efraim Turban,et al.  Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real-World Performance , 1992 .

[4]  Jure Leskovec,et al.  Patterns of temporal variation in online media , 2011, WSDM '11.

[5]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[6]  Isabell M. Welpe,et al.  Tweets and Trades: The Information Content of Stock Microblogs , 2010 .

[7]  Rui Wang,et al.  Towards social user profiling: unified and discriminative influence model for inferring home locations , 2012, KDD.

[8]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[9]  Philip S. Yu,et al.  Detecting Leaders from Correlated Time Series , 2010, DASFAA.

[10]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[11]  Patrik Idvall,et al.  Algorithmic Trading : Hidden Markov Models on Foreign Exchange Data , 2008 .

[12]  Ellen Riloff,et al.  Learning Extraction Patterns for Subjective Expressions , 2003, EMNLP.

[13]  Eric Gilbert,et al.  Widespread Worry and the Stock Market , 2010, ICWSM.

[14]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[15]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[16]  Yingjian Zhang,et al.  PREDICTION OF FINANCIAL TIME SERIES WITH HIDDEN MARKOV MODELS , 2004 .

[17]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[18]  Claire Cardie,et al.  OpinionFinder: A System for Subjectivity Analysis , 2005, HLT.

[19]  John R. Nofsinger.  Social Mood and Financial Economics , 2005 .

[20]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[21]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[22]  Bing Liu,et al.  Sentiment Analysis and Subjectivity , 2010, Handbook of Natural Language Processing.

[23]  Xue-Qi Cheng,et al.  Trading Network Predicts Stock Price , 2014, Scientific Reports.

[24]  Jinglu Hu,et al.  An SVM-based approach for stock market trend prediction , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[25]  Isabell M. Welpe,et al.  Tweets and Trades: The Information Content of Stock Microblogs , 2010 .

[26]  Christian S. Jensen,et al.  Travel Cost Inference from Sparse, Spatio-Temporally Correlated Time Series Using Markov Models , 2013, Proc. VLDB Endow..

[27]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[28]  Ran El-Yaniv,et al.  Selective Prediction of Financial Trends with Hidden Markov Models , 2011, NIPS.

[29]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[30]  Hsinchun Chen,et al.  A Discrete Stock Price Prediction Engine Based on Financial News , 2010, Computer.

[31]  Chao Wang,et al.  Improving Stock Market Prediction by Integrating Both Market News and Stock Prices , 2011, DEXA.

[32]  Xiaotie Deng,et al.  Exploiting Topic based Twitter Sentiment for Stock Prediction , 2013, ACL.

[33]  Ran El-Yaniv,et al.  On the Foundations of Noise-free Selective Classification , 2010, J. Mach. Learn. Res..