Forecasting inflation with twitter

Abstract

We use Twitter content to generate an indicator of attention allocated toinflation. The analysis corresponds to Argentina for the period 2012 2019.The attention index provides valuable information regarding future levelsof inflation. A one standard deviation increment in the index is followed byan increment of approximately 0.4% in expected inflation in the consecutive month. Out-of-sample exercises confirm that social media contentallows for gains in forecast accuracy. Beyond point forecasts, the indexprovides valuable information regarding inflation uncertainty. The proposed indicator compares favorably with other indicators such as mediacontent, media tweets, google search intensity and consumer surveys.