PhD Thesis

My PhD thesis is entitled « Construction of Model Behavior by Novices through Interaction with Machine Learning ». I am being supervised by Jules Françoise, Baptiste Caramiaux, and Michèle Gouiffès. In this thesis, we consider ML models as sociotechnical artifacts whose behavior unfolds through users’ interaction with them, focusing on how novices can surface, negotiate, and contest that behavior in context. Across the thesis, I examine interaction as a site where people assert their perspectives, challenge dominant assumptions, and make visible what models overlook. Rather than seeking to expose a single hidden logic, my thesis invites deeper engagement with the social, political, and epistemic conditions that shape ML systems, toward a more participatory and reflexive vision of human-centered AI. I hope my work opens space for practices that make ML systems more accountable, interpretable, and open to change.