The Power of Text-based Indicators in Forecasting the Italian Economic Activity

Abstract

Can we use newspaper articles to forecast economic activity? Our answer is yes and, to this aim, we propose a brand new economic dictionary in Italian with valence shifters, and we apply it on a corpus of about two million articles from four popular newspapers. We produce a set of high-frequency text-based sentiment and policy uncertainty indicators (TESI and TEPU, respectively), which are timely, not revised and computed both for the whole economy and for specific sectors or economic topics. To test the predictive power of our text-based indicators, we propose two forecasting exercises. First, using Bayesian Model Averaging (BMA) techniques, we show that our monthly text-based indicators greatly shrink the uncertainty surrounding the short-term forecasts of the main macroeconomic aggregates, especially during recessions. Secondly, we employ these indexes in a weekly GDP growth tracker, delivering sizeable gains in forecasting accuracy in both normal and turbulent times.

Nowcasting Euro Area GDP with News Sentiment: A Tale of Two Crises

“…Within the Euro area, Aguilar et al (2021) show that their sentiment indicator derived from Spanish newspapers is comparable to the sentiment index produced by the European Commission and more helpful in nowcasting GDP. Similarly, Aprigliano et al (2021) build sentiment and uncertainty indices for Italy and provide evidence of sizeable gains in forecast accuracy, both in normal and turbulent times, when forecasting several macroeconomic aggregates.…”