Can Twitter analysis predict next-day stock returns?

A study from West Virginia University suggests the social media platform could be a useful tool for investment firms

Can Twitter analysis predict next-day stock returns?
Steve Randall

When Elon Musk tweeted about Tesla’s share price back in May, it resulted in the company’s value slumping $14 billion.

Market-moving posts on social media may attract the attention of regulators – as a previous Musk tweet about Tesla did in 2018 when the Securities and Exchange Commission (SEC) filed a complaint against the entrepreneur.

But outside of outbursts from CEOs, can posts on Twitter reveal insights of use to investors?

Yes, according to a new study from West Virginia University which concludes that Twitter posts can influence stock returns and that firm-level tweets could be useful for predicting next-day stock returns.

WVU professor and finance expert Alexander Kurov and the co-authors of the study, "Informational role of social media: Evidence from Twitter sentiment,” used Bloomberg data which classifies individual tweets about a given company, aggregated it and branded the resulting variable "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 said “Our results show, however, that Twitter sentiment contains relevant information not yet reflected in stock prices.”

Investment strategy
The study authors were prompted to research how social media could be used as an investment strategy due to the SEC’s decision in 2013 to allow companies to post news such as quarterly earnings on Twitter and its subsequent increased use by high-profile firms and investors such as Warren Buffett.

In their paper, they 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," said Kurov.

While other studies have looked at Twitter message content, this one went a step further by testing systematically if these messages contain useful information about thousands of individual stocks.

Kurov says that traders should look carefully at social media content and firms should improve transparency and market efficiency by using these platforms.

Stock manipulation?
While the study, published in the Journal of Banking and Finance, found that stock prices can be influenced by Twitter posts, Kurov is not convinced that the platform could be used to systematically manipulate stocks.

"If a Twitter feed consistently disseminates information that is not factual, investors will quickly figure this out," he said. "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."

LATEST NEWS