My teaching aims to foster intrinsic motivation, critical engagement, and independent reasoning, especially in methodologically demanding courses where students must connect abstract tools to substantive questions. Whether working with data or applying theory, I encourage the active and responsible use of generative and agentic technologies as instruments that augment human judgment and creativity rather than replace it.
This doctoral course introduces methods for analyzing large-scale text data, such as natural language processing, sentiment analysis, text classification, and topic modeling. Students learn to build and preprocess corpora, implement text-as-data methods in R, and critically evaluate their suitability for different research questions. Through a combination of seminars, coding sessions, and applied assignments, the course equips participants to integrate computational text analysis into their own research and field.
This master-level course provides an analytical framework for understanding digital platforms such as online marketplaces, search engines, and social media. Students apply economic theory and empirical methods to analyze business models, competition in multi-sided markets, and policy implications. Particular emphasis is placed on reproducibility and the responsible use of causal inference and machine learning techniques, including transformer-based language models.
“Thank you for creating a friendly and intellectually stimulating classroom environment.”
Methods to Analyze Text as Data
Spring 2023
“The Data Day was one of the highlights of this semester”
Platform Economics
Spring 2025
“Engaging and talented at breaking down complicated topics into understandable pieces.”
Introduction to Economic Thought
Autumn 2022