Journal of Economics and Finance

, Volume 34, Issue 1, pp 96–112 | Cite as

Are day traders bias free?—evidence from internet stock message boards



This study addresses the issue whether day traders’ recommendations on stocks are biasfree. We test whether on average day traders’ “Hold” sentiment is skewed and different from a neutral opinion. Posted messages and mature text classifier technology provide a novel approach to analyze the content of these “Hold” sentiment postings among day traders. Findings indicate that the self-disclosed “Hold” sentiment conveys an optimistic opinion and significantly differs from neutral. These results help both investors and researchers to better understand day traders’ psychology and behaviors when they recommend stocks. The paper also provides insight into the construction of future online sentiment indexes based on stock message boards.


Internet Stock Message Boards Retail Investor Sentiment Sentiment Bias Day Traders Text Classifiers 

JEL Classification

G11 G12 


  1. Admati AR, Pfleiderer PC (2001) Disclosing information on the internet: is it noise or is it news? Technical report, Graduate School of Business, Stanford UniversityGoogle Scholar
  2. Antweiler W, Frank MZ (2004) Is all that talk just noise? The information content of internet stock message boards. J Finance 59(3):1259–1295. doi:10.1111/j.1540-6261.2004.00662.x CrossRefGoogle Scholar
  3. Asquith P, Mikhail MB, Au AS (2005) Information content of equity analyst reports. J Financ Econ 75:245–282. doi:10.1016/j.jfineco.2004.01.002 CrossRefGoogle Scholar
  4. Barber BM, Odean T (2001) The internet and the investor. J Econ Perspect 15:41–54CrossRefGoogle Scholar
  5. Barber B, Lehavy R, McNichols M, Trueman B (2001) Can investors profit from the prophets? Consensus analyst recommendations and stock returns. J Finance 56:531–563. doi:10.1111/0022-1082.00336 CrossRefGoogle Scholar
  6. Barber B, Lehavy R, McNichols M, Trueman B (2006) Buys, holds, and sells: the distribution of investment banks’ stock ratings and the implications for the profitability of analysts’ recommendations. J Account Econ 41:87–117. doi:10.1016/j.jacceco.2005.10.001 CrossRefGoogle Scholar
  7. Bender O, Macherey K, Och FJ, Ney H (2003) Comparison of alignment templates and maximum entropy models for natural language understanding, Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics, Budapest, Hungary: 11–18Google Scholar
  8. Berger AL, Della Pietra VJ, Della Pietra SA (1996) A maximum entropy approach to natural language processing. Comput Linguist 22(1):39–71Google Scholar
  9. Carleton WT, Chen CR, Steiner TL (1998) Optimism biases among brokerage and non-brokerage firms’ equity recommendations: agency costs in the investment industry. Financ Manag 27(1):17–30. doi:10.2307/3666148 CrossRefGoogle Scholar
  10. Choi WS, Cho JM, Seo J (1999) Analysis system of speech acts and discourse structures using maximum entropy model. Proceedings of the 37th conference on Association for Computational Linguistics, Morgan Kaufman, San Francisco, 230–237Google Scholar
  11. Das SR, Chen MY (2003) Yahoo! for Amazon: sentiment parsing from small talk on the Web, Proceedings of the 8th Asia Pacific Finance Association annual conference, Working paperGoogle Scholar
  12. Das SR, Chen MY (2007) Yahoo! for Amazon: sentiment extraction from small talk on the Web. Manage Sci 53:1375–1388. doi:10.1287/mnsc.1070.0704 CrossRefGoogle Scholar
  13. D’Avolio G, Gildor E, Shleifer A (2002) Technology, information production, and market efficiency Economic Policy for the Information Economy, A Symposium Sponsored by the Federal Reserve Bank of Kansas CityGoogle Scholar
  14. DeMarzo P, Vayanos D, Zwiebel J (2003) Persuasion bias, social influence, and uni-dimensional opinions. Q J Econ 118:909–968. doi:10.1162/00335530360698469 CrossRefGoogle Scholar
  15. Estabrooks A, Jo T, Japkowicz N (2004) A multiple resampling method for learning from imbalances data sets. Comput Intell 20(1):18–36. doi:10.1111/j.0824-7935.2004.t01-1-00228.x CrossRefGoogle Scholar
  16. Fernandez R, Ginzburg J, Lappin S (2005) Using machine learning for non-sentential utterance classification. Proceedings of the Sixth SIGDJIAl Workshop on Discourse and DJIAlogue, Lisbon, 77–86Google Scholar
  17. Friedman JH (1997) On bias, variance, 0/1-loss, and the curse of dimensionality. Data Min Knowl Discov 1:55–77. doi:10.1023/A:1009778005914 CrossRefGoogle Scholar
  18. Glaser M (2003) Online broker investors: demographic information, investment strategy, portfolio positions, and trading activity, working paper. University of MannheimGoogle Scholar
  19. Gu B, Konana P, Liu A, Rajagopalan B, Ghosh J (2006) Predictive value of stock message board sentiments, working paper. the University of Texas at AustinGoogle Scholar
  20. Hirschey M, Richardson VJ, Scholz S (2000) How “foolish” are internet investors. Financ Anal J 56:62–69. doi:10.2469/faj.v56.n1.2331 CrossRefGoogle Scholar
  21. Japkowicz N, Stephen S (2002) The class imbalance problem: a systematic study. Intell Data Anal J 6(5):429–450Google Scholar
  22. Jegadeesh N, Kim J, Krische SD, Lee CMC (2004) Analyzing the analysts: when do recommendations add value. J Finance 59:1083–1124. doi:10.1111/j.1540-6261.2004.00657.x CrossRefGoogle Scholar
  23. Joachimes T (1997) A probabilistic analysis of the rocchio algorithm with TFIDF for text categorization. In Proceedings of Fourteenth International Conference on Machine Learning, 143–151, Nashiville, TN, 1997. Morgan KaufmannGoogle Scholar
  24. Komaromi G (2002) Why have the stock markets become noisier after the revolution of information and technology. In Evolutions of Institutions and the Knowledge Economy Conference Proceedings. University of DebrecenGoogle Scholar
  25. Konana P, Menon N, Balasubramanian S (2000) The implications of online investing. Commun ACM 43(1):34–41. doi:10.1145/323830.323842 CrossRefGoogle Scholar
  26. Koski JL, Rice EM, Tarhouni A (2007) Noise trading and volatility: evidence from day trading and message boards, working paper, University of WashingtonGoogle Scholar
  27. Lau R, Rosenfeld R, Roukos (1993) Adaptive language modeling using the maximum entropy principle. In Proceedings of the ARPA Human Language Technology Workshop, published as Human Language Technology, 108–113Google Scholar
  28. McCallum AK (1996) Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering,∼mccallum/bow
  29. Michaely R, Womack KL (1999) Conflict of interest and the credibility of underwriter analyst recommendations. Rev Financ Stud 12:653–686. doi:10.1093/rfs/12.4.653 CrossRefGoogle Scholar
  30. Odean T (1999) Do investors trade too much. Am Econ Rev 89:1279–1298Google Scholar
  31. Oh NY, Parwada JT, Walter TS (2004) Online investors’ trading behaviour and performance: evidence from the Korean equity market. Working paper, University of New South WalesGoogle Scholar
  32. Pettibone J, Pon-Barry H (2003) A maximum entropy approach to recognizing discourse relations in spoken language. Working paper, The Stanford Natural Language Processing Group. June 6Google Scholar
  33. Ratnaparkhi A (1997) A simple introduction to maximum entropy models for natural language processing. Technical Report 97-08, Institute for Research in Cognitive Science. University of PennsylvaniaGoogle Scholar
  34. Ratnaparkhi A (1998) Maximum entropy models for natural language ambiguity resolution, PhD thesis, University of PennsylvaniaGoogle Scholar
  35. Rennie JDM, Shih L, Teevan J, Karger DR (2003) Tackling the poor assumptions of naive Bayes text classifiers. In: Fawcett T, Mishra N (eds), International Conference on machine learning, Washington D.C, Morgan KaufmannGoogle Scholar
  36. Rosenfeld R (1996) A maximum entropy approach to adaptive statistical language modeling. Computer, Speech, and Language, 10:187–228CrossRefGoogle Scholar
  37. Sabherwal S, Sarkar KS, Zhang Y (2008) Online-talk, does it matter? Manage Finance 34(6):423–436. doi:10.1108/03074350810872813 Google Scholar
  38. Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv 34(1):1–47. doi:10.1145/505282.505283 CrossRefGoogle Scholar
  39. Shefrin H, Statman M (1985) The disposition to sell winners too early and ride losers too long: theory and evidence. J Finance 40(3):777–790. doi:10.2307/2327802 CrossRefGoogle Scholar
  40. Tumarkin R (2002) Internet message board activity and market efficiency: a case study of the internet service sector using Financ Mark Inst Instrum 11:313–335. doi:10.1111/1468-0416.11403 CrossRefGoogle Scholar
  41. Tumarkin R, Whitelaw RF (2001) News or noise? Internet message board activity and stock prices. Financ Anal J 57(3):41–51. doi:10.2469/faj.v57.n3.2449 CrossRefGoogle Scholar
  42. Unsal F, Movassaghi H (2001) Impact of internet on financial services industry: a case study of online investing. Managerial Finance 27(7):54–65 . doi:10.1108/03074350110767295 CrossRefGoogle Scholar
  43. Wysocki PD (1999) Cheap talk on the web: the determinants of postings on stock message boards. Working paper, University of MichiganGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Department of Economics and FinanceMonmouth UniversityWest Long BranchUSA
  2. 2.Department of Finance and Real EstateUniversity of Texas at ArlingtonArlingtonUSA

Personalised recommendations