In Quest of Significance: Identifying Types of Twitter Sentiment Events that Predict Spikes in Sales

We study the power of Twitter events to predict consumer sales events by analysing sales for 75 companies from the retail sector and over 150 million tweets mentioning those companies along with their sentiment. We suggest an approach for events identification on Twitter extending existing methodologies of event study. We also propose a robust method for clustering Twitter events into different types based on their shape, which captures the varying dynamics of information propagation through the social network. We provide empirical evidence that through events differentiation based on their shape we can clearly identify types of Twitter events that have a more significant power to predict spikes in sales than the aggregated Twitter signal.

[1]  Steve Y. Yang,et al.  An empirical study of the financial community network on Twitter , 2013, 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr).

[2]  Amir Rubin,et al.  The Impact of Business Intelligence Systems on Stock Return Volatility , 2007, Inf. Manag..

[3]  Wei Jiang,et al.  On-line outlier detection and data cleaning , 2004, Comput. Chem. Eng..

[4]  E. Fama,et al.  The Adjustment of Stock Prices to New Information , 1969 .

[5]  Soo-Min Kim,et al.  Crystal: Analyzing Predictive Opinions on the Web , 2007, EMNLP.

[6]  Daniel E. O'Leary,et al.  Event Study Methodologies in Information Systems Research , 2011, Int. J. Account. Inf. Syst..

[7]  Michael J. Cafarella,et al.  Using Social Media to Measure Labor Market Flows , 2014 .

[8]  Connie St Louis,et al.  Can Twitter predict disease outbreaks? , 2012, BMJ : British Medical Journal.

[9]  Didier Sornette,et al.  Robust dynamic classes revealed by measuring the response function of a social system , 2008, Proceedings of the National Academy of Sciences.

[10]  Isabell M. Welpe,et al.  News or Noise? Using Twitter to Identify and Understand Company‐Specific News Flow , 2014 .

[11]  Misako Takayasu,et al.  Empirical analysis of collective human behavior for extraordinary events in blogosphere , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[13]  Jerold B. Warner,et al.  Using daily stock returns: The case of event studies , 1985 .

[14]  Mizuki Morita,et al.  Twitter Catches The Flu: Detecting Influenza Epidemics using Twitter , 2011, EMNLP.

[15]  Brad M. Barber,et al.  Detecting Long-Run Abnormal Stock Returns: The Empirical Power and Specification of Test Statistics , 1997 .

[16]  D. Sornette,et al.  Endogenous Versus Exogenous Shocks in Complex Networks: An Empirical Test Using Book Sale Rankings , 2003, Physical review letters.

[17]  M. Mitchell,et al.  The Role of Financial Economics in Securities Fraud Cases: Applications at the Securities and Exchange Commission , 2016 .

[18]  Roman Beck,et al.  It's More about the Content than the Users! The Influence of Social Broadcasting on Stock Markets , 2015, ECIS.

[19]  F. Hampel.  A General Qualitative Definition of Robustness , 1971 .

[20]  Aron Culotta,et al.  Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages , 2012, Language Resources and Evaluation.

[21]  Guido Caldarelli,et al.  Investigating the Relations between Twitter Sentiment and Stock Prices , 2015, ArXiv.

[22]  Eamonn Keogh.  Exact Indexing of Dynamic Time Warping , 2002, VLDB.

[23]  G. Schwert.  Using Financial Data to Measure Effects of Regulation , 1981, The Journal of Law and Economics.

[24]  Werner Antweiler,et al.  Is All that Talk Just Noise? The Information Content of Internet Stock Message Boards , 2001 .

[25]  Philip C. Treleaven,et al.  Twitter Sentiment Analysis Applied to Finance: A Case Study in the Retail Industry , 2015, ArXiv.

[26]  Ekaterina Shabunina.  Correlation between Stock Prices and polarity of companies' performance in Tweets: a CRF-based Approach , 2015 .

[27]  Durga Toshniwal,et al.  Using Cumulative Weighted Slopes for Clustering Time Series Data , 2005 .

[28]  Brian Dickinson,et al.  Sentiment Analysis of Investor Opinions on Twitter , 2015 .

[29]  Tomaso Aste,et al.  When Can Social Media Lead Financial Markets? , 2014, Scientific Reports.

[30]  Mark Dredze,et al.  You Are What You Tweet: Analyzing Twitter for Public Health , 2011, ICWSM.

[31]  Bernardo A. Huberman,et al.  Predicting the Future with Social Media , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[32]  J. P. Park.  The Identification Of Multiple Outliers , 2000 .

[33]  B. Rosner.  Percentage Points for a Generalized ESD Many-Outlier Procedure , 1983 .

[34]  Remco M. Dijkman,et al.  Using Twitter to Predict Sales: A Case Study , 2015, ArXiv.

[35]  Joel E. Thompson,et al.  More Methods That Make Little Difference In Event Studies , 1988 .

[36]  Jerold B. Warner,et al.  MEASURING SECURITY PRICE PERFORMANCE , 1980 .

[37]  Preslav Nakov,et al.  SemEval-2013 Task 2: Sentiment Analysis in Twitter , 2013, *SEMEVAL.

[38]  Isabell M. Welpe,et al.  Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment , 2010, ICWSM.

[39]  Ramanathan V. Guha,et al.  The predictive power of online chatter , 2005, KDD '05.

[40]  S. P. Kothari,et al.  Econometrics of Event Studies , 2007 .

[41]  Wen-Hsien Tsai,et al.  Will eChannel additions increase the financial performance of the firm?—The evidence from Taiwan , 2007 .

[42]  A. Smeaton,et al.  On Using Twitter to Monitor Political Sentiment and Predict Election Results , 2011 .

[43]  F. Hampel.  The Influence Curve and Its Role in Robust Estimation , 1974 .

[44]  A. Mackinlay,et al.  Event Studies in Economics and Finance , 1997 .

[45]  Aliza Sarlan,et al.  Twitter sentiment analysis , 2014, Proceedings of the 6th International Conference on Information Technology and Multimedia.

[46]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[47]  Nello Cristianini,et al.  Flu Detector - Tracking Epidemics on Twitter , 2010, ECML/PKDD.

[48]  Raymond T. Ng,et al.  Indexing spatio-temporal trajectories with Chebyshev polynomials , 2004, SIGMOD '04.

[49]  D. Sornette,et al.  Endogenous versus Exogenous Origins of Crises , 2004, physics/0412026.

[50]  Peter N Bell.  New methodology for event studies in Bonds , 2010 .