Tensor-Based Implementation for Joint Sentiment Topic Modeling
Methods for Large Scale Text Data
Research Projects
Some of my latest work on frontier methods for Political Methodology.
Republicans perceive scientists are Democrats, but they can be persuaded to be more trustful of scientific findings
Americans perceive latent partisanship of scientists, and this influences their trust in scientific findings.
If a Statistical Model Predicts That Common Events Should Occur Only Once in 10,000 Elections, Maybe it’s the Wrong Model
Statistical description is not anything goes. Important quantities of interest arise from generatively accurate models— which inform our understanding of American democracy.
Persuadable voters decided the 2022 midterm
Abortion rights and issues-based frameworks for elections
Highly polluting fossil fuel firms reframe climate and sustainability communication on social media
We provide a new data-driven foundation for understanding the structure of influential stakeholders' online conversations in the climate and sustainability space.
Eroding Trust in Democracy
How Social Media Attacks on Election Officials in 2020 Undermined American Election Institutions
Dynamics of Political Polarization
Insights from Using Machine Learning and Natural Language Processing with Twitter Data
Why don’t Americans trust university researchers and why it matters for climate change
We examine the multivariate correlates of trust in university research and opinions about climate change using high-quality survey data.
Legislative Communication and Power
Measuring Leadership in the U.S. House of Representatives from Social Media Data