'Bullish' tweets offer clues to stock performance

New York: Can financial intelligence be found in the "twitterverse" which can provide clues to how a stock will perform? Yes, says a team from Johns Hopkins University.

A strong co-relation does exist between the mood of a day's worth of tweets about a particular stock and the performance of that stock, added Jim Kyung-Soo Liew from Hopkins' Carey Business School.

"When Apple does well within the day, participants are tweeting with bullish sentiment, showing that a positive correlation exists between contemporaneous price movements and tweet sentiments," Liew stated.

The new paper, forthcoming in The Journal of Portfolio Management, shows that tweet-like posts on the StockTwits financial micro-blogging platform are strongly related over a given day to the behaviour of the stock being tweeted about during that day.

According to Liew, this use of social media to determine stock performance should be added as a "sixth factor" to the Fama-French five-factor model well known in financial circles as a method for explaining market behaviour.

Liew and his co-author associate professor Tamas Budavari of the Hopkins Krieger School of Arts and Sciences were granted access to all StockTwits posts about 15 companies that drew the most Twitter commentary from January 2012 to October 2015.

The companies were Apple, Facebook, Netflix, Yahoo, Amazon, Google, Disney and American Airlines, among others.

People who post on StockTwits can state in their tweets whether they feel positive ("bullish") or negative ("bearish") about a stock.

Mining this data, the researchers discovered "a particular intuitive relationship between tweet sentiment and prices over time."

"Namely, we show that the aggregated daily sentiment matters for equity daily returns. Positive sentiment is associated with positive returns," they wrote.

Some critics say the real-time status of a tweet can make it irrelevant after, say, minutes or hours.

But Liew begs to differ. "There appears to exist a strong positive relationship between the daily time-series of aggregated tweet sentiments and their corresponding security returns," he pointed out in a university statement.

A previous study that Liew wrote for The Journal of Portfolio Management found a strong link between the mood of Twitter posts and the performance of an initial public offering (IPO).