Information demand in the modern world is met to a huge extent by information supply from the search engine Google. Humans use the search engine to gather information which shall help to reduce perceived personal uncertainty about a specific subject. Google Trends is providing insights into this information demand in a timely manner and for a variety of different countries. In this paper, multinational Google Trends data and unsupervised learning techniques are used to construct meaningful country clusters resembling the economic, geographic and political relationships of the considered countries. Additionally, these clusters are stable over time. Under the assumption that an increase in Google search requests reflect elevated uncertainty, the cluster information is used to construct economic and political uncertainty time series for 43 different countries. This uncertainty index Granger causes quarterly GDP growth in more countries compared to an existing multinational uncertainty index proofing its usefulness in the field of forecasting. Furthermore, the new index is available up to a daily frequency and can be applied to additional countries and regions.

No abstract

Several studies have shown that uncertainty among economic actors influences business cycle dynamics. This paper uses Google Trends topic queries to construct an uncertainty proxy that can be applied to every country where Google is active. Using a VAR approach, this paper demonstrates that the obtained impulse-response functions of main economic indicators to a one-standard deviation shock to the constructed indicator, are similar to those from an already-existing uncertainty proxy, the EPU. This is true for the G7 countries and Russia. On average, the uncertainty indicator constructed for this paper leads to more statistically significant responses than does the EPU. Thus, this paper shows that Google Trends is a helpful tool for obtaining timely information about uncertainty among economic actors. The main improvement in this uncertainty proxy is in its language independence. Existing uncertainty-measurement approaches, in contrast, rely on certain keywords that often vary across countries.