Word embeddings for topic modeling: An application to the estimation of the economic policy uncertainty index

Abstract

The quantification of economic uncertainty is key to the prediction of macroeconomic variables, such as gross domestic product (GDP), and is particularly crucial in regard to real-time or short-time prediction methodologies, such as nowcasting, where a large amount of time series data is required. Most of the data comes from official agency statistics and non-public institutions, but these sources are susceptible to lack of information due to major disruptive events, such as the COVID-19 pandemic. Because of this, it is very common nowadays to use non-traditional data from different sources. The economic policy uncertainty (EPU) index is the indicator most frequently used to quantify uncertainty and is based on topic modeling of newspapers. In this paper, we propose a methodology to estimate the EPU index that incorporates a fast and efficient method for topic modeling of digital news based on semantic clustering with word embeddings, allowing us to update the index in real time, which is something that other studies have failed to manage. We show that our proposal enables us to update the index and significantly reduce the time required for new document assignation into topics.