Does StockTwits Predict the Stock Market?

Over the past 18 months, there has been a growing body of research exploring whether the river of tweets produced by Twitter has predictive value with the stock market.

In October 2010, Bollen and colleagues published a study entitled Twitter mood predicts the stock market which suggests that measurements of the collective mood states derived from the analysis of large scale Twitter feeds did just that.

Soon after, Derwent Capital raised $40 million and launched a hedge fund incorporating Twitter sentiment analysis as a component of the investing strategy based on Bollen et al.’s methodology.

Much more recently, Chong Oh and Olivia R Lui Sheng published a study entitled Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Stock Price Directional Movement which utilized StockTwits messages exclusively.

The StockTwits data is solely focused on markets and highly organized as StockTwits messages are tagged by stock tickers using the StockTwits $ cashtag and members are expressly focused on market analysis, trades, news and links.

Hence, more signal, less noise.

Utilizing the StockTwits data, Oh and Sheng concluded that,

…investor sentiment as expressed in stock micro blog postings does appear to have strong predictive value for future market directions.

They also suggested that the StockTwits messaging format contributed to their ability to derive significant results, stating,

We establish that the stock micro blog with its succinctness, high volume and real-time features do have predictive power over future stock price movements.

Having participated in and closely observed the StockTwits stream since the beginning, I am not surprised by the researchers’ findings. The crowdsourced nature of the StockTwits stream zeros in on and amplifies new information and analysis so quickly that often we see a stock ticker begin to trend before the majority of a corresponding move in the stock occurs.

Oh and Sheng’s work supports the underreaction hypothesis, a much studied and popular proposal among behavioral economists, which posits that asset prices tend to underreact to new information and only slowly drift over time towards new values which account for the news.

Its my suspicion that as research moves from academia to quantitative analysis performed by money managers, they will discover a variety of anomalies, only some of which might be explained by underreaction.

Tim Richards at The Psy-Fi Blog penned a thoughtful summary of the research and wrote,

I don’t know if StockTwits sentiment analysis can really predict market movements over any time period, but I will make a prediction. Someone, somewhere, is building a system to trade on the possibility. It’s an arms race, and in arms races its usually the side with the deepest pockets and the smartest people that wins. Only, in a world of globally networked social media it’s not so obvious who that’s going to be.

You betcha Tim!



blog comments powered by Disqus
StockTwits Blog