How news affects the trading behaviour of different categories of investors in a financial market

We investigate the trading behaviour of a large set of single investors trading the highly liquid Nokia stock over the period 2003-2008 with the aim of determining the relative role of endogenous and exogenous factors that may affect their behaviour. As endogenous factors, we consider returns and volatility, whereas the exogenous factors are the total daily number of news articles and a semantic variable based on a sentiment analysis of the news. Linear regression and partial correlation analysis of the data show that different categories of investors are differently correlated to these factors. Governmental and non-profit organizations are weakly sensitive to news and returns or volatility, and, typically, they are more correlated with the former than with the latter. Households and companies, on the contrary, are very sensitive to both endogenous and exogenous factors, and volatility and returns are, on average, much more relevant than the number of news articles and sentiment, respectively. Financial institutions and foreign organizations are intermediate between these two cases, in terms of both the total explanatory power of these factors and their relative importance. We explicitly consider the role of overnight news and overnight returns on the successive trading activity and trading balance of the different categories of investors. We observe the role of the overnight news, which is weaker than the ones observed between synchronous variables. By performing a vector autoregression (VAR) analysis, we show that the flux of news of the previous day affects the trading activity of companies, households and foreign investors and the dynamics of volatility. VAR is not detecting any role of the lagged sentiment in the successive values of the difference between the number of buying and selling investors for each category of investors.