nach oben

Journal of Economics and Finance

Erschienen in:

03.09.2019

Stock returns and investor sentiment: textual analysis and social media

verfasst von: Zachary McGurk, Adam Nowak, Joshua C. Hall

Erschienen in: Journal of Economics and Finance | Ausgabe 3/2020

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

The behavioral finance literature has found that investor sentiment has predictive ability for equity returns. This differs from standard finance theory, which provides no role for investor sentiment. We examine the relationship between investor sentiment and stock returns by employing textual analysis on social media posts. We find that our investor sentiment measure has a positive and significant effect on abnormal stock returns. These findings are consistent across a number of different models and specifications, providing further evidence against non-behavioral theories.

Vorheriger Artikel Firm size proxies and the value relevance of predictive stock return models

Nächster Artikel U.S. Small Business Administration loans and U.S. state-level employment

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

See, for example, Baker and Wurgler (2006) and Baker and Wurgler (2007).

See Bukovina (2016) and Zhou (2018) for a review of the recent literature.

Loughran and McDonald (2011) include a method for weighting individual words, however, this is based on word frequency rather than perceived sentiment information.

Bloomberg and Thompson Reuters have created commercial equity specific textual analysis based investor sentiment measures. These measures are proprietary and as such estimation methods are unknown. These measure are used by Sun et al. (2016) and Behrendt and Schmidt (2018).

Source: Twitter 2018 Annual Report.

http://www.wjh.harvard.edu/∼inquirer/homecat.htm

See Loughran and McDonald (2016) for an extended discussion of alternative weighting schemes.

We thank the anonymous reviewer for providing an additional critique of the bag-of-words approach without token weighting.

In 2017, Twitter increased character limits to 280. As the twitter data used in study is from prior to this change, all tweets are limited to 140 characters.

Alternative approaches can be taken that would allow for continuous classifications.

StockTwit is social media platform where by users primarily discuss topics relating to financial markets.

We utilize the MNIR method to first obtain a set of tweets relevant information. Further information on this method can be provided upon request.

Because the tweets frequently indicate the direction of the stock (up or down), we modify a list of stop words from the SnowballC package in R to retain finance-specific words.

In unreported results, we found our quantitative results were not substantially impacted by this procedure. However, the list of significant tokens is impacted by this procedure, as expected.

We use the convention where different words in a bigram are separated by “.”

See https://www.mturk.com/ for information on the Amazon Mechanical Turk service.

To limit the effect of outliers, we only include daily Returns in between -50 and 50 percent.

Bigram and Unigram coefficient estimates are available upon request.

As a note, due to the change in the daily value of market capitalization, some stocks would be part of a different decile at different dates.

Interested readers can find them in the working paper version of this article, available at https://researchrepository.wvu.edu/econ∖_working-papers/.

Alternative model specifications including additional variables are also estimated. Results are relatively similar to the results from Eq. 15. These are available upon request. Due to data limitations, we only use a one day forecast horizon.

We would like to thank the anonymous reviewer for noting non-linear forecasting models, as employed in Bekiros et al. (2016), would likely produce larger gains in forecast accuracy compared to a linear model for both approaches. Including a non-linear forecasting model in our paper does not allow for a direct comparison between our tokenization approach and the previous literature so we do not pursue it here. However, this is an excellent idea for future papers.

Available at https://researchrepository.wvu.edu/econ∖_working-papers/.

Aboody D, Even-Tov O, Lehavy R, Trueman B (2018) Overnight returns and firm-specific investor sentiment. J Financ Quant Anal 53(2):485–505CrossRef

Avery C, Chevalier J (1999) Identifying investor sentiment from price paths: The case of football betting. J Bus 72(4):493–520CrossRef

Baker M, Wurgler J (2006) Investor sentiment and the cross-section of stock returns. J Financ 61(4):1645–1680CrossRef

Baker M, Wurgler J (2007) Investor sentiment in the stock market. J Econ Perspect 21(2):129–152CrossRef

Baker M, Wurgler J, Yuan Y (2012) Global, local, and contagious investor sentiment. J Financ Econ 104(2):272–287CrossRef

Bartov E, Faurel L, Mohanram PS (2018) Can twitter help predict firm-level earnings and stock returns? Accounti Rev 93(3):25–57CrossRef

Behrendt S, Schmidt A (2018) The Twitter myth revisited: Intraday investor sentiment, Twitter activity and individual-level stock return volatility. J Bank Financ 96:355–367CrossRef

Bekiros S, Gupta R, Kyei C (2016) A non-linear approach for predicting stock returns and volatility with the use of investor sentiment indices. Appl Econ 48 (31):2895–2898CrossRef

Brown GW, Cliff MT (2004) Investor sentiment and the near-term stock market. J Empir Financ 11(1): 1–27CrossRef

Bukovina J (2016) Social media big data and capital markets – an overview. J Behav Exper Financ 11: 18–26CrossRef

Chen H, De P, Hu YJ, Hwang B. -H. (2014) Wisdom of crowds: The value of stock opinions transmitted through social media. Rev Financ Stud 27(5):1367–1403CrossRef

Chung S-L, Hung C-H, Yeh C-Y (2012) When does investor sentiment predict stock returns? J Empir Financ 19(2):217–240CrossRef

Clark TE (2004) Can out-of-sample forecast comparisons help prevent overfitting? J Forecast 23(2): 115–139CrossRef

Clark TE, McCracken MW (2005) The power of tests of predictive ability in the presence of structural breaks. J Econ 124(1):1–31CrossRef

Da Z, Engelberg J, Gao P (2015) The sum of all FEARS investor sentiment and asset prices. Rev Financ Stud 28(1):1–32CrossRef

Frijns B, Verschoor WF, Zwinkels RC (2017) Excess stock return comovements and the role of investor sentiment. J Int Financ MarketInstit Money 49:74–87CrossRef

Heston SL, Sinha NR (2017) News vs sentiment: Predicting stock returns from news stories. Financ Anal J 73(3):67–83CrossRef

Huang D, Jiang F, Tu J, Zhou G (2015) Investor sentiment aligned: a powerful predictor of stock returns. Rev Financ Stud 28(3):791–837CrossRef

Inoue A, Kilian L (2005) In-sample or out-of-sample tests of predictability: Which one should we use? Econ Rev 23(4):371–402CrossRef

Jiang F, Lee J, Martin X, Zhou G (2019) Manager sentiment and stock returns. J Financ Econ 132(1):126–149CrossRef

Lee WY, Jiang CX, Indro DC (2002) Stock market volatility, excess returns, and the role of investor sentiment. J Bank Financ 26(12):2277–2299CrossRef

Lemmon M, Portniaguina E (2006) Consumer confidence and asset prices: Some empirical evidence. Rev Financ Stud 19(4):1499–1529CrossRef

Loughran T, McDonald B (2011) When is a liability not a liability? Textual analysis, dictionaries, and 10-ks. J Financ 66(1):35–65CrossRef

Loughran T, McDonald B (2014) Measuring readability in financial disclosures. J Financ 69(4): 1643–1671CrossRef

Loughran T, McDonald B (2016) Textual analysis in accounting and finance: a survey. J Account Res 54(4):1187–1230CrossRef

Malkiel BG, Fama EF (1970) Efficient capital markets: a review of theory and empirical work. J Financ 25(2):383–417CrossRef

Mitra T, Gilbert E (2014) The language that gets people to give: Phrases that predict success on Kickstarter. In: Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing. ACM, pp 49–61

Ni Z-X, Wang D-Z, Xue W-J (2015) Investor sentiment and its nonlinear effect on stock returns – new evidence from the Chinese stock market based on panel quantile regression model. Econ Model 50:266–274CrossRef

Oliveira N, Cortez P, Areal N (2016) Stock market sentiment lexicon acquisition using microblogging data and statistical measures. Decis Support Syst 85:62–73CrossRef

Ranco G, Aleksovski D, Caldarelli G, Grčar M, Mozetič I (2015) The effects of Twitter sentiment on stock price returns. PloS One 10(9):e0138441CrossRef

Renault T (2017) Intraday online investor sentiment and return patterns in the US stock market. J Bank Financ 84:25–40CrossRef

Schmeling M (2009) Investor sentiment and stock returns: Some international evidence. J Empir Financ 16(3):394–408CrossRef

Seok SI, Cho H, Ryu D (2018) Firm-specific investor sentiment and daily stock returns. The North American Journal of Economics and Finance

Shen J, Yu J, Zhao S (2017) Investor sentiment and economic forces. J Monet Econ 86:1–21CrossRef

Smales LA (2017) The importance of fear: Investor sentiment and stock market returns. Appl Econ 49(34):3395–3421CrossRef

Sprenger TO, Sandner PG, Tumasjan A, Welpe IM (2014a) News or noise? Using Twitter to identify and understand company-specific news flow. J Bus Financ Account 41(7-8):791–830

Sprenger TO, Tumasjan A, Sandner PG, Welpe IM (2014b) Tweets and trades: The information content of stock microblogs. Eur Financ Manag 20(5):926–957

Sun L, Najand M, Shen J (2016) Stock return predictability and investor sentiment: a high-frequency perspective. J Bank Financ 73:147–164CrossRef

Taddy M (2013a) Measuring political sentiment on Twitter: Factor optimal design for multinomial inverse regression. Technometrics 55(4):415–425

Taddy M (2013b) Multinomial inverse regression for text analysis. J Am Stat Assoc 108(503):755–770

Weisenthal J (2011) 50 Cent’s tweets make a staggering $50 million in one day. Business Insider, 10 January

Xu H-C, Zhou W-X (2018) A weekly sentiment index and the cross-section of stock returns. Financ Res Lett 27:135–139CrossRef

Yang SY, Mo SYK, Liu A (2015) Twitter financial community sentiment and its predictive relationship to stock market movement. Quant Financ 15(10):1637–1656CrossRef

Yang C, Zhou L (2016) Individual stock crowded trades, individual stock investor sentiment and excess returns. North Amer J Econ Financ 38:39–53CrossRef

Zhou G (2018) Measuring investor sentiment. Ann Rev Financ Econ 10:239–259CrossRef

Titel: Stock returns and investor sentiment: textual analysis and social media
verfasst von: Zachary McGurk
Adam Nowak
Joshua C. Hall
Publikationsdatum: 03.09.2019
Verlag: Springer US
Erschienen in: Journal of Economics and Finance / Ausgabe 3/2020
Print ISSN: 1055-0925
Elektronische ISSN: 1938-9744
DOI: https://doi.org/10.1007/s12197-019-09494-4

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 3/2020

Real activities manipulation in stock-for-stock mergers

Market fragmentation and post-earnings announcement drift

Managerial optimism, CEO retention, and corporate performance: evidence from bankruptcy-filing firms

Efficiency in the madness? examining the betting market for the ncaa men’s basketball tournament

Risk factors explaining returns anomaly in emerging market banks – study on Indian banking system

U.S. Small Business Administration loans and U.S. state-level employment