Nowcasting food insecurity interest with google trends data

This research explores the potential of Google Trends (GT) data as a tool for generating a daily index of food insecurity at the national level, focusing on regions monitored by the Famine Early Warning Systems Network (FEWS NET) and the Global Fragility Act (GFA). Drawing inspiration from previous studies on GT's predictive capabilities, the authors employ Natural Language Processing (NLP) to analyse food security reporting from FEWS NET documents. We identify key predictors of food insecurity using a LASSO regression approach and construct a daily economic sentiment index (DESI) for each country. Unlike traditional methods, the study considers multiple languages and weights search terms based on LASSO coefficients. The resulting Synthetic Search Interest (SSI) index for food insecurity demonstrates a statistically significant correlation with FAO's share of the population in severe food insecurity, affirming GT's potential as a monitoring tool. The research contributes a novel methodology and insights into leveraging real-time data for early warnings in food security.