A presentation by Lynn Kaack (Hertie School). This event is part of the Political Economy Lunch Seminar (PELS).
In policy research, large and systematic assessments of documents are often lacking, as analyzing text manually is labor-intensive and costly. Machine learning offers a new set of approaches that can help address this bottleneck. This talk will cover several examples from climate and energy policy, where natural language processing (NLP) techniques from machine learning are used to automatically analyze large bodies of text. Such applications include analyzing the policy design of renewable energy legislation, drawing insights from patent claims about innovation policy, and analyzing climate-related financial disclosures.
Lynn Kaack is Assistant Professor of Computer Science and Public Policy at the Hertie School. Her research and teaching focuses on methods from statistics and machine learning to inform climate mitigation policy across the energy sector, and on climate-related AI policy. She is a co-founder and chair of Climate Change AI, which is an organization to facilitate work at the intersection of machine learning and climate action. Previously she was Postdoctoral Researcher and Lecturer in the Energy Politics Group at ETH Zürich. She obtained a PhD in Engineering and Public Policy and a Master's in Machine Learning from Carnegie Mellon University, as well as a MS and BS in Physics from the Free University of Berlin.