This article exploits two newspaper archives to track economic policy uncertainty in Spain from 1905–1945. We find that the outbreak of the Civil War in 1936 was anticipated by a striking upward level shift of uncertainty in both newspapers. We study the reasons for this shift through a natural language processing method, which allows us to leverage expert opinion to track specific issues in our newspaper archives. We find a strong empirical link between increasing uncertainty and the rise of divisive political issues like socio-economic conflict. This holds even when exploiting content differences between the two newspapers in our corpus.
Our interpretation of our findings is that Spain experienced a civil war because its political institutions could not deal with internal socio-economic conflict. Even though de jure political power was at times in the hand of the workers, reforms were blocked by the de facto power of land owners (see Acemoglu & Robinson (2006)) which made the conflict escalate. In this way the Spanish case sounds a warning to an ongoing tendency in Western democracies to polarize politically and an increased readiness to engage in political violence around the world.
In hindsight I think the simple tf-idf method we adopted in this paper is the beating heart of the paper. The simple method is so powerful that I have made it part of my teachin in text analysis.
The published version can be downloaded freely here. Paper has been published as a the CEPR paper number 15479 and a Barcelona GSE working paper. The latest version can also be downloaded here.
