Dirk Wulff

The course introduces the use of open-source large language models (LLMs) from the Hugging Face ecosystem for research in the behavioral and social sciences. In short lectures, participants will learn about key concepts (e.g., embeddings, causal attention, feature extraction, classification, prediction, fine-tuning, and token generation) and practical examples from social and behavioral science. In hands-on exercises, participants will apply language models to answer research questions from psychology, political science, decision-making research, and other fields. During and after the course, participants will engage in a personal research project applying LLMs to a personal research question. Two lecturers will hold this course, implying a high level of support during the exercises and research project design.

LLMs (think ChatGPT) are incredibly useful tools for research in the social and behavioral sciences. In this course, you will (1) learn about the fundamental principles of LLMs, (2) learn how to employ open-source LLMs using the Hugging Face ecosystem, (3) learn about the rich opportunities that LLMs offer for behavioral and social science research, and (4) gain experience in applying LLMs to answer personal research questions.

Learning objectives The creation and communication of data visualizations is a critical step in any data analytic project. Modern open-source software packages offer ever more powerful data visualizations tools. When applied with psychological and design principles in mind, users competent in these tools can produce data visualizations that easily tell more than a thousand words. In this course, participants learn how to employ state-of-the-art data visualization tools within the programming language R to create stunning, publication-ready data visualizations that communicate critical insights about data. Prior to, during, and after the course participants work their own data visualization project. Course content Each day will contain a series of short lectures and demonstrations that introduce and discuss new topics. The bulk of each day will be dedicated to hands-on, step-by-step exercises to help participants ‘learn by doing’. In these exercises, participants will learn how to read-in and prepare data, how to create various types of static and interactive data visualizations, how to tweak them to exactly fit one’s needs, and how to embed them in digital reports. Accompanying the course, each participant will work on his or her own data visualization project turning an initial visualization sketch into a one-page academic paper featuring a polished, well-designed figure. To advance these projects, participants will be able to draw on support from the instructors in the afternoons of course days two to four.