Prior to joining SCARP, Madison worked in nuclear physics, applied mathematics, and data science. Now, she seeks to meaningfully apply her technical experience to making urban systems more sustainable, understanding the interconnectedness of infrastructure, people, and the environment, and identifying how our urban designs have left certain groups without access to basic services. She uses machine learning to study how the language in an individual’s information environment shapes their perceptions and norms around sustainable behaviors in three crucial transition spaces: housing, transportation, and energy.
From signals to support: Uncovering the language of sustainable transitions with machine learning
My research leverages extensive experience in data science to analyze the impact of informal signals, such as online posts or news broadcast commentaries, on an individual's support and uptake of sustainable behaviors. I explore this through three critical sustainable transition spaces: housing, transportation, and energy. My work shows that large-scale norms, and the language used to convey them, influence individuals’ perceptions of desirable qualities of people and conditions in dense rental living, sustainable transportation modes, and renewable energy projects regardless of the actual benefits or drawbacks of these systems. This research provides evidence about the power of the social dimensions of sustainable transitions as well as the language used to perpetuate it.
