My research sits at the intersection of social science, data science, and artificial intelligence. I am particularly interested in how computational methods can help us understand human behaviour and address complex societal problems. A central theme of my work is moving beyond prediction alone: I use machine learning and large-scale data to investigate why people behave differently, when behaviour is predictable, and how computational approaches can contribute to the development and testing of social-scientific theory.
A second strand of my research focuses on developing and critically examining AI and machine-learning methods for the social sciences. This includes explainable and interpretable AI, the integration of machine learning with traditional statistical approaches, and questions around measurement, fairness, ethics, and responsible use. I am especially interested in methods that are not only technically effective, but also interpretable and useful to researchers and the people affected by algorithmic systems.
My work is interdisciplinary and spans a range of substantive areas, including environmental and educational psychology, climate change and sustainability, human wellbeing, inequality, and human rights. Across these domains, I am interested in combining social-scientific theory with novel data sources and computational methods to understand complex patterns of human behaviour and, ultimately, to generate insights that are both scientifically meaningful and socially useful.
Follow this link for further information
