Tweets and Trades: the Information Content of Stock Microblogs

Abstract

Microblogging forums (e.g., Twitter) have become a vibrant online platform for exchanging stock‐related information. Using methods from computational linguistics, we analyse roughly 250,000 stock‐related messages (so‐called tweets) on a daily basis. We find an association between tweet sentiment and stock returns, message volume and trading volume, as well as disagreement and volatility. In contrast to previous related research, we also analyse the mechanism leading to an efficient aggregation of information in microblogging forums. Our results demonstrate that users providing above average investment advice are retweeted (i.e., quoted) more often and have more followers, which amplifies their share of voice.

Trading on Twitter: Using Social Media Sentiment to Predict Stock Returns

“…Users have integrated social media into many aspects of their daily life (Ellison, 2007), including investment decision making (Oh & Sheng, 2011). Numerous professional and amateur investors and analysts use Twitter to post news articles, and opinions, often providing information and comments more frequently than the professional news media (Sprenger, Tumasjan, Sandner, & Welpe, 2014).…”

“…They found the 5-day rolling average of the bullishness index was useful in predicting stock price movements. Sprenger et al (2014) also used machine learning to create a different bullishness index that they too found to be predictive of stock returns several days later. Smailović, Grčar, Lavrač, andŽnidaršič (2014) used machine learning to examine sentiment (i.e., positive emotion) in tweets and found it to be predictive of stock returns several days later.…”

Trader Participation in Disclosure: Implications of Interactions with Management

“…Our study makes several contributions. First, our study contributes to the emerging literature investigating how social media affects the disclosure process (e.g., Blankespoor et al 2014;Chen et al 2014;Sprenger et al 2013). We answer recent calls to better understand how managers can anticipate and manage their firms' new information environments given the increasingly widespread interactive nature of social media platforms (Miller and Skinner 2015).…”

Are economically significant bond returns explained by corporate news? An examination of the German corporate bond market

“…Recent research focusing on several event categories predominantly uses broad news sources. Antweiler and Frank (2004), for instance, employ a large sample of Internet messages and Sprenger et al (2013) choose Twitter announcements to analyze how news influences stock markets. Earlier literature had to work with news published in paper form, which is expected to be a fairly slow source of information, potentially causing a misallocation between information and price movements.…”

“…Given the real-time character of this database, there are fewer distortions in the flow of information than might occur when using news published in newspapers. Following Antweiler and Frank (2004) and Sprenger et al (2013), we used a linguistic classification algorithm to assign each announcement to a specific news category. At first, we manually classified 1000 randomly selected announcements from our event data set in a dual-control process to create a training sample containing all default news categories.…”