Abstract
Among the statistical techniques used to describe the behaviour of the financial markets, one of the most promising is based on the network analysis of the stock market. In this framework, the stock market is represented as a graph with nodes (the single stocks), edges (connections between stocks), and attributes (industry classification, volumes ...). The application of network analysis to the stock market is not new, but in previous contributions the market graph has been mainly derived from the correlationmatrix of the stock prices. This is a limitation, and the risks are to express in different words what traditional financial econometrics has already said about the returns' distribution. Moreover, if we want to use network analysis not only as a descriptive tool but also as an inference instrument, we need other data than the correlation matrix itself. For this reason, we integrated the analysis and built the market graph with new type of data taken from the observation of the information gathering activity performed by retail investors through the Google's search engine. We focussed the attention on financial crises, when a shock hits the economy in such a profound way that almost all the parameters entering the pricing equation of stocks must be reassessed. Those periods are relatively rare and short. They are characterised by extremely high levels of volatility and correlation. In these moments, searching for new information becomes of paramount importance. And then it is in these moments that we expect to observe more neatly the working of the underlying network.