Research interest

In my research, I am primarily interested in the potential of machine learning to predict differences in how individuals react to environmental conditions (reactivities). Specifically, my dissertation investigates whether differences in reactivities can be reliably predicted, and which person-level variables have the strongest influence on this prediction. I am investigating this in different contexts (e.g., social situations, education) for different types of reactivities (e.g., well-being, abilities) using different data sources (e.g., experience sampling, learning history data).

In my approach, I combine data-driven bottom-up approaches with theoretically informed top-down approaches, especially for the derivation of the considered reactivities. Furthermore, I use modern methods from explainable artificial intelligence, which allow to identify important robust predictors and predictor combinations for the prediction, thus providing important suggestions for further theory building. Moreover, I aim to highlight the limitations of current statistical methods and strive to develop them further for adequate prediction of individual differences in reactivities.

In addition to my dissertation topic, I am interested in several other innovative topics in the field of psychological diagnostics and personality psychology. In particular, I am interested in the influence of personality on the perception of and interaction with new technologies and the possibilities these technologies offer for personality research. This includes interpersonal simulations, VR-based scenarios, and Large Language Model-based interactions.