Markets and the mind
Examining the effect of public opinion on stock market returns and harnessing social sentiment to make quantitative market predictions.
The rise and fall of the stock market is highly dependent on public opinion. As news travels among investors, they make decisions which directly affect stock values. It is now possible to track people’s engagement with the news through their digital footprint and interactions on social media. By analysing such data, we can uncover correlations between interactions with the news and the behaviour of the market.
In this project, we study web search, Twitter and news outlet data to discover hidden indicators of financial markets. We show that the volume of web search queries of individual stocks over short times is predictive of stock prices. In addition, we can identify the sentiment of tweets from textual analysis by using supervised learning methods. With this, correlations between social media and markets during key news events can be clearly picked out. Finally, while the effect of news stories on markets cannot be deduced from the stories alone, the extent of interactions with them can forecast price movements.
The collective behaviour of investors is responsible for financial swings and crises. By using sophisticated analyses of people’s online interactions with financial-related news, downturns can be predicted and crises mitigated.
News sentiment analysis and web browsing data are unilluminating alone, but inspected together, predict fluctuations in stock prices.
When the number of tweets about an event peaks, the sentiment of those tweets correlates strongly with abnormal stock market returns.
Analysis of web search queries about a given stock, from the seemingly uncoordinated activity of many users, can anticipate the trading peak.