How Sentiment Analysis via Twitter can help you Beat the Market
Estimated reading time: 2 minutes, 27 seconds
How much power can be gained from 140 characters you wonder? Well in the case of the Derwent Capital Hedge Fund market an awful lot. In May this year Derwent Capital Hedge Fund started trading using algorithms and a trading model that follow comments posted on Twitter.
Paul Hawtin who is the hedge fund manager of Derwent stated that “For years investors have widely accepted that financial markets are driven by fear and greed but we’ve never before had the technology or data to be able to quantify human emotions.” Now we do. This newly developed algorithm allows is based on a research paper from the University of Manchester and Indian University which concluded that there was a strong correlation between the mood on Twitter and the rise/fall of stock and commodity prices in the FTSE 100 and the Dow Jones. There are now 175 million users on Twitter producing around 95 million posts per day, a pot of gold for data analysts and mathematicians who have already started to find new ways to analyse rapidly growing source of real time data.=
According to the Atlantic Wire:
“The number of emotional words on Twitter could be used to predict daily moves in the Dow Jones Industrial Average. A change in emotions expressed online would be followed between two and six days later by a move in the index, the researchers said, and this information let them predict its movements with 87.6 percent accuracy”
These are pretty remarkable results. The rise in value of a stock, commodity or even a product doesn’t always have to be in regards to positive internal or external factors; it can just be perceived value. Outside of the realm of stock and commodities the perceived value is usually the result of successful brand building efforts but it could also be the result of media outlets continuously informing you what is “fashionable”, “ethical” or “uncool”. It is measuring this attitude that can help determine future behaviour, Paul Hawtin went on to discuss how the “Sentiment and mood dramatically change the impact of positive and negative news stories. If the market’s in a very positive and bullish mood, it can shrug off bad news…. bad news comes out and you expect the Dow to fall, and it doesn’t.”
Using web-based data, especially snippets from social networks, to build a real-time measure of users’ emotions and preferences is not new and neither is using the data to predict future behaviour. According to the Economist other algorithms are being used to exploit social media activity, “WiseWindow, a marketing firm based in Irvine, California, uses social-media activity to forecast demand for products. Its clients include Paramount Pictures and Belkin, a consumer-electronics firm.” This poses the question what other markets it could be valuable for and more importantly why didn’t South East Rail use this before they decided to hike the prices up for the 3rd consecutive year….