Abstract

Abstract International climate change negotiations primarily occur during annual Conferences of the Parties (COPs) to the United Nations Framework Convention on Climate Change and currently involve virtually every country in the world. What effect does such a large and heterogeneous group of states have on the complexity of climate change negotiations? Would a smaller, more homogenous, assortment of countries produce a more efficient negotiation space? To begin to answer these questions, I apply Latent Dirichlet Allocation to a corpus of Highlevel climate change conference speeches, covering the formal statements made by country-representatives at the 16th-to-19th COPs. This exercise yields a very large and coherent set of latent topics and many, but not all, of these topics correspond to the negotiating positions presumed by extant research. Analysis of the resultant topics reveals that the dominant dimensions of climate change negotiation favor developing country concerns over cooperation, though reducing negotiations to a smaller core group of countries may lessen this disparity. Together these findings indicate that unsupervised topic models can substantially expand our understandings of climate change negotiations, and international cooperation more generally.