Talk, Language and Computation Seminar Series, School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK
Political science scholars working with large quantities of textual data are often interested in discovering latent semantic structures in their document collections. Examples include legislative debates, policies, media content, manifestos, and open-ended survey questions. Domain idiosyncrasies often do not allow direct application of standard NLP toolkit. This talk will introduce several recent applications in the areas of climate change politics, international relations, legislative politics, and armed conflict prediction.