Can Twitter Help Predict Firm-Level Earnings and Stock Returns?

Abstract

Prior research has examined how companies exploit Twitter in communicating with investors, and whether Twitter activity predicts the stock market as a whole. We test whether opinions of individuals tweeted just prior to a firm's earnings announcement predict its earnings and announcement returns. Using a broad sample from 2009 to 2012, we find that the aggregate opinion from individual tweets successfully predicts a firm's forthcoming quarterly earnings and announcement returns. These results hold for tweets that convey original information, as well as tweets that disseminate existing information, and are stronger for tweets providing information directly related to firm fundamentals and stock trading. Importantly, our results hold even after controlling for concurrent information or opinion from traditional media sources, and are stronger for firms in weaker information environments. Our findings highlight the importance of considering the aggregate opinion from individual tweets when assessing a stock's future prospects and value.

Social Determinants of Success: Social Media, Corporate Governance and Revenue

“…Notable research topics on social media and social capital include the following: the reasons for using the Internet and participating in online social networking sites [12]; linkages between social capital and opportunities in foreign markets and exports [13][14][15]; the way that social networks can provide tacit knowledge about international business practices [16][17][18]; the linkages between social media and business performance [9,[19][20][21][22]; the way that social networks can help address financial crises [23]; the use of social media to predict stock movements in financial markets [24][25][26]; employee creativity; and even the ability of social networks to help predict real world outcomes [27].…”

Recente inzichten in het gebruik van alternatieve prestatiemaatstaven door beursgenoteerde ondernemingen

“…Tegelijkertijd blijft de stijging in het gebruik van non-GAAP-verslaggeving een belangrijk punt van aandacht voor toezichthouders. Er is tegenwoordig een gigantische hoeveelheid aan ondernemingsspecifieke informatie beschikbaar via het internet en sociale media (Blankespoor et al 2013;Chen et al 2014;Jame et al 2016;Drake et al 2017;Bartov et al 2018;Blankespoor et al 2018;Tang 2018). Tevens is er voldoende bewijs in de literatuur om te kunnen concluderen dat de meeste beleggers slechts beperkte tijd en middelen hebben om al deze informatie te verwerken en tot de juiste beslissingen en waarderingen te komen (Hong et al 2007;Hirshleifer et al 2009;Cohen and Lou 2012;Lee and So 2015;Dehaan et al 2017;Veenman and Verwijmeren 2018).…”

Crowdsourced Financial Analysis and Information Asymmetry at Earnings Announcements

“…Recent research suggests that social media plays an increasingly important role in financial markets. For instance, research finds that Twitter content helps disseminate value relevant news (Tang 2017;Bartov, Faurel, and Mohanram 2018). Jame et al (2016) find that crowdsourced earnings forecasts available on Estimize.com are incremental to analyst forecasts in predicting future earnings surprises.…”

“…While early research suggests that crowdsourced "analysis" on internet bulletin boards is mostly noise (e.g. Antweiler and Frank 2004), more recent research suggests that crowdsourced information is value relevant (Chen et al 2014;Jame et al 2016;Tang 2017;Campbell, DeAngelis, and Moon 2018;Hales, Moon, and Swenson 2018;Bartov, Faurel, and Mohanram 2018). Given the proliferation and relative ease with which anyone can acquire crowdsourced financial analysis, including less sophisticated investors who lack the information acquisition and processing resources of more sophisticated investors, we ask whether crowdsourced financial analysis helps alleviate the information asymmetry problem at earnings announcements.…”

“…First, we contribute to a growing literature on social media, crowdsourced information, and nontraditional information intermediaries. To date, research suggests analysis produced on crowdsourced platforms provides value relevant information about firms (e.g., Chen et al 2014;Jame et al 2016; Campbell, DeAngelis, and Moon 2018; Tang 2017; Bartov, Faurel, and Mohanram 2018), plays an important role in information dissemination (Blankespoor, Miller, and White 2014), and, depending on the source, improves price efficiency (Drake, Thornock, and Twedt 2017). All of this research focuses on the basic notion that crowdsourced information can help improve properties of price formation.…”