Twitter is the go-to place for chatter about what's happening right now, but could the collective hive mind actually predict events? Researchers think so.
Analysis of more than one million Twitter posts by scientists at the Rotterdam School of Management found that they could predict stock market movements and help traders make decisions on investments.
An algorithm analysed the tweets mentioning the S&P 100 share index and classed the stock as either a buy, hold, or sell, just like human anlaysts, based on the sentiment. The rating was then compared to the actual share price movements in the following days.
Bullish sentiment was found to be linked with higher abnormal returns, while the number of tweets about a particular stock could predict trading volumes, volatility and follow-up return on a stock. They also found that the higher the disagreement about a stock, the higher the trading volumes.
“This study shows the potential value of information on twitter for making informed trading decisions," said professor of digital business Ting Li who lead the research with Dr Jan van Dalen.
"In the simulation we showed that if you invested money in the S&P 100 and used the information gleaned from twitter using our algorithm, you would beat the market. You could invest in one company or a number, you could sell at the end of each day and reinvest the next or you could trade every other day or every 3, 4 or 5 days – and even when you take transaction costs into consideration, you’d still come out ahead," he claimed.
“This could be used by institutional investors or home-based day traders and proves that twitter isn’t just noise – useful information can be extracted and could help investors make better decisions," he added.
Research by the European Central Bank has also indicated that Twitter talk can predict stock movements, while the Bank of England has said it could help it predict market movements, unemployment data and even a bank run.