BIS Seminar: Associate Professor Marten Risius

15 March, 2019 - 10:30 to 12:00
Joyce Ackroyd (37), Room 430

Social media Enabled Business Analytics

The efficient market hypothesis assumes that stock prices are solely dependent on the rational processing of information and, thus, cannot be predicted. However, we assume that social influences on social media platforms affect information dissemination and, ultimately, stock returns.

In this regard, several events have shown that information proliferated on Twitter can have substantial effect on stock prices. Twitter is used to share opinions about companies and to reveal evaluations about the performance of companies’ stocks. Such messages are received by investors who integrate the information into their decision making. The information drawn from social media platforms is also processed by investment companies, stock exchanges, and news providers using data analytics to generate insights to stock market participants.

Estimating how shared, social media content will influence stock market investors’ decision making, advances predictive financial analytics. However, little is known about the short-term relation between social media activities and stock markets. In this study, we study (a) whether buy- and sell-signals of Twitter messages have a predictive power of stock prices, and (b) how the influence of users and messages relate to this effect. We analyze 5 million stock-related Twitter messages issued about the S&P 100 companies, and identify buy- and sell-signals by applying a supervised text mining algorithm.

Based on stock market data on a minute basis, we focus on short-term effects of the messages, and measure how they change within 15 to 60 minutes. The results confirm that financial predictive analytics needs to focus on negative messages especially from users with a large follower base across all time-frames. Analyzing the spread if negative messages shows that the share original messages are only relevant within the first 15 minutes, within 30 minutes only the retweet numbers matter in determining stock prices.

Associate Professor Marten Risius

Marten Risius is Assistant Professor in the Department of Management at the Clemson University, SC, USA. His research interests revolve around managerial and societal concerns regarding social media and blockchain technologies. His articles have been published in various international journals and peer-reviewed conferences. He has been internationally recognized with various academic and industry awards as well as through research grants. His work is also featured in public media, for example, by The Boston Globe.