Title: Political cohesion and economic growth: The case of GDP for Italy Authors:  Alessandra Amendola - University of Salerno (Italy)
Walter Distaso - Imperial College London (United Kingdom)
Alessandro Grimaldi - University of Salerno (Italy) [presenting]
Abstract: The purpose is to derive new textual political polarity indices based on the text analysis of the entire collection of the Italian Senate of the Republic verbatim reports. The procedure allows for building a set of polarity indices reflecting the impact of the tone of political debate - as well as agreement/disagreement within political groups - on a specific economic variable over time. Time series regressions on the yearly Italian GDP growth rate point to a nontrivial predictive power of the proposed polarity indices, which, importantly - differently from common practice in related textual analysis literature - rely on a machine learning approach rather than the subjective choice of an affective lexicon.