Projects from my research and applied AI work.
These are the projects I keep coming back to in conversation. Each one used a different method — an experiment, a corpus, a coding scheme, an applied workflow — but I started each from a real question and tried to stay honest about what came out.
Each card walks through one project — the question, the design, the method, and my role. For the formal record, see the publications page.
Unsupervised Machine Learning for Social Cognition
Using unsupervised machine learning to reveal hidden patterns in human beliefs and attitudes.
My role
Lead author.
What it contributes
A tutorial and applied methods paper where I show how K-means, DBSCAN, PCA, and market basket analysis can reveal structure in large-scale attitude data.
Why Reform Stalls
Modeling public justification, outrage, and reform discourse around police violence.
My role
Conceived and led the project; conceptualization, methodology, data curation, formal analysis, validation, investigation, visualization, and writing.
What it contributes
A public IPR working paper where I pair large-scale YouTube comment analysis with an experiment to study how justification and outrage relate to reform discourse around police violence.
Historical Blame and Collective Responsibility
Understanding why people hold present-day groups responsible for past harms.
My role
Coauthor.
What it contributes
Research on psychological antecedents of historical blame, including perceived connectedness between past and present groups, current benefit or harm, and unresolved obligations.
Energy Company / Landowner Negotiation Data
Studying negotiation dynamics and equity in hydraulic fracturing land acquisition.
My role
Contributor on data collection and coding-scheme development; the public supplement names me alongside several coauthors for those contributions.
What it contributes
An interdisciplinary Nature Energy project analyzing how energy companies negotiate with landowners and how institutional contexts shape bargaining power.