This PhD defense presents computational approaches to human behavior across two domains. First, a construct-mining pipeline uses open-ended responses, sentence embeddings, debiasing, HDBSCAN clustering, and intrusion validation to derive a data-driven taxonomy of emotion regulation strategies. Second, mixed-methods and classifiers analyze German Twitter, linking counter-speech styles to hate reduction at scale.

This research examines sexual harassment and cyberbullying in online gaming, highlighting how women and gender-diverse players face disproportionate harm. By analysing real player disclosures and addressing the disconnect between gamer experience and research definitions, the project aims to develop accurate, community-informed prevention programs to better protect players and reduce online harassment.