The role of political leadership for economic development has recently gained interest in economics. However, empirically testing the influence of leaders remains challenging since there is not an agreed-upon measure of “good political leadership”. We show that quantifying leaders’ professed agendas through their public statements provides a viable means for studying the role of leadership for economic development. Taking advantage of recent developments in machine learning, we apply Latent Dirichlet Allocation (LDA) to quantify the thematic contents of U.S’governors’ speeches, and show a positive association between U.S governors commitment to business promotion and business expansion in their states. We further demonstrate that the thematic contents of leaders’ speeches are proxies for their professed priorities. The U.S governors’ State of the State Addresses (SoSAs) are used as a test case, since these speeches are by design meant to lay out the governors’ priorities. Our findings illustrate the usefulness of topic modeling in analyzing political speech and suggest that speeches may be useful in identifying the role of leadership in economic development. (JEL O10, R50, C38)
More detail can easily be written here using Markdown and $\rm \LaTeX$ math code.