Since 2022, traditional methods of social science research in Russia — including fieldwork and surveys — have become increasingly difficult to implement. At the same time, a wide range of administrative, digital, and textual data remains available, allowing researchers to study social, political, and economic processes indirectly. During the workshop we focused on working with Russian court decisions as a large-scale textual dataset.

Participants will examine the use of large language models (LLMs) to extract entities and structured information from legal texts, with attention to practical workflows and validation issues. Alexander Keysut is an economist and data analyst with many years of experience working on open data projects in Russia. He contributed to the development of a court decisions parser covering Russian courts — a tool downloaded several hundred times by researchers and independent journalists, and used as the basis for more than a dozen published investigations and analytical pieces. Alexander specializes in large-scale data processing, statistical analysis, and building data infrastructure for civic and research purposes, with deep expertise in working with Russian administrative and judicial datasets.