Trading with Twitter: Study reveals how tweets can seriously influence stock returns

MORGANTOWN, W.Va. — Twitter and similar social media platforms have become incredibly influential in the worlds of politics, sports, and news. Now, a new study finds that posts on social media can also influence stock returns.

Alexander Kurov, a West Virginia University financial expert, says that firm-level Twitter posts indeed offer useful information for predicting next-day stock returns. Furthermore, he says such Twitter content is a stronger predictor of returns for firms with less analyst coverage.

To come to these conclusions, researchers used data provided by Bloomberg. That data consisted of individual tweets that had been categorized and then aggregated to determine “Twitter sentiment.”

“Academic research in finance generally shows that investor sentiment tends to be driven by investor beliefs or feelings not justified by fundamentals, such as facts and rational expectations that should determine the value of a stock,” Kurov says in a university release. “Our results show, however, that Twitter sentiment contains relevant information not yet reflected in stock prices.”

“In particular, we show that Twitter sentiment contains information about upcoming analyst recommendation changes, analyst target price changes, quarterly earnings surprises and opening prices of stock initial public offerings,” he adds. Some AI options trading platforms now provide sentiment and social media alerts.

Tweets can both help and hurt your stocks

Public firms have been allowed to display news and quarterly earnings reports on Twitter since 2013. Since then, many financial giants like Warren Buffet have taken to the platform to spout their opinions. These developments motivated the study’s authors to begin this research.

Sometimes, information is leaked on Twitter before it should be, sparking big changes in stock prices. For example, in 2016 the results of a clinical trial for a new diabetes drug were presented at a conference. Everyone in attendance was supposed to keep the presentation confidential, but within minutes the story had broke on Twitter. By the next day, the drug manufacturer’s stock had dropped by over five percent due to less than stellar clinical results.

“On the one hand, it is possible that tweets mentioning companies have little new relevant information,” Kurov explains. “In that case, Twitter content is just random noise that should have no permanent effect on stock prices. On the other hand, Twitter may aggregate bits and pieces of relevant information from diverse sources. We wanted to see which of these two plausible stories has more support in the data. Some previous studies have looked at information content of Twitter messages, but we were the first to test systematically if these messages contain useful information about thousands of individual stocks.”

Don’t trust everything you hear online

According to Kurov, traders should look to Twitter periodically for news. Entities should also continue posting transparent information on such platforms. Importantly, however, researchers don’t think firms or investors can systematically manipulate stocks using Twitter.

“If a Twitter feed consistently disseminates information that is not factual, investors will quickly figure this out,” the study author concludes. “Furthermore, spreading false information with intent to manipulate security prices is illegal and could make the person doing that a target of an investigation by the Securities and Exchange Commission.”

The study is published in the Journal of Banking and Finance.