Project Description
Financial regulators and central banks are increasingly integrating sustainability aspects into their operations. At the same time, regulatory developments aimed at harmonizing company-level disclosures on sustainability issues notwithstanding, significant data gaps remain. One particular challenge is that companies communicate their sustainability information through unstructured reports that contain both numerical and textual data. To make this information amenable to comparative research, GIST applies Natural Language Processing (NLP) and Large Language Models (LLMs) for data extraction. By doing so, the project aims to make methodological contributions to the NLP field and produce substantial insights on companies’ sustainability performance by means of systematically extracting data for established and new indicators.