300270 Computational Social Sciences (LEH: Soziologische Methoden - quantitativ) (LEH) (SoSe 2024)

Computational social science (CSS) has emerged as a significant research field over the years. While different descriptions and definitions are available, CSS is best defined as a research approach that utilizes computational methods, often in conjunction with big and unstructured data, to investigate research questions in social science disciplines such as sociology, political science, and economics. Common methods involve applying machine learning and natural language processing algorithms to datasets collected from a range of social media and other online sources.

This course („Lehrforschung“, Module 30-M-Soz-M3_LF1) provides an extensive overview of data sources, methods, and applications in Computational Social Sciences. The course covers topics such as data types and data sources, algorithms and computational performance, online and social media data, web scraping and API usage, handling big data sets, processing of text data, data visualisation and research data management. Above all, we will also discuss which questions can be answered with the help of Computational Social Science and its methods, where possible limitations lie, and what constitutes good Computational Social Science research.

Students will make use of the statistical software R to apply newfound knowledge in a practical setting. Students will develop their own research question and project, which they will work on during the semester (possibly in groups with several students). Access to the computing cluster of the Faculty of Sociology will be provided, making it possible to get some valuable experience in analysing big data in a high performance computing environment.

The seminar will be held in English. Assigments (Studienleistung) will also be in English. The term paper (Lehrforschungsbericht) can be conducted in English or German. Some practical knowledge about working with data is required (e.g. knowledge of univariate statistics or the previous use of another statistical software such as SPSS or STATA). Knowledge of R is advantageous, but a very brief introduction will be given to students with no prior knowledge to catch up on their own.