Ruben Bach, Mannheim Centre for European Social Research (MZES): New Data and Methods for Social Science Research (June 2024)

Ruben Bach is a research fellow in the Data and Methods Unit of the Mannheim Centre for European Social Research (MZES). His research is rooted in computational social science. It tackles questions of online news media consumption, AI-guided decision-making, and quality aspects of novel and traditional data products in the social sciences.

What is your current research topic?                                 

One project I like combines research from two topics that have been on my research agenda for some years. I combine knowledge from survey methodology, a field in applied statistics that studies survey data collection methods and the ways to optimize them, with statistical learning techniques for analyzing textual data. For example, I study which survey and questionnaire designs result in the highest response quality and, at the same time, produce data in formats that are optimal for automated or semi-automated analysis using natural language processing algorithms.   

For those who have not yet delved deeply into the topic of Data Science: How would you explain to a child what you are working on?

I study how we should ask questions to people in ways that their answers accurately describe what they think. At the same time, the answers should come in formats that make it easy for computer programs to understand them. It's like crafting the perfect questionnaire that can be easily read and understood by both people and computers.

Everyone talks about Data Science – how would you describe the importance of the topic for yourself in three words?

Data quality is everything (4 words, close enough I hope)

What points of contact with Data Science does your work have? Which methods do you already use, and which would be interesting for you in the future?

I use all kinds of machine learning algorithms for applied research in the social sciences. So far, I have focused on transformer-based language models and various algorithms based on classification and regression trees. In the future, I want to add techniques for dealing with audiovisual data to my portfolio.

How high is the value of Data Science for your work? Would your research even be possible without Data Science?

It depends on the definition of data science. My work has always been concerned with data and data analysis techniques. Following that logic, my job would not be possible without data science.

What development opportunities do you see for the topic of Data Science in relation to your field?

I believe that social scientists, and especially methodologists like me, should contribute more to research on understanding quality aspects of the data used. High-quality data are essential for making good decisions. So far, we often focus too much on the algorithms and the analysis pipelines and too little on the data we use.

Back