We are a research collective dedicated to providing public communication campaigns with rigorous, state-of-the-art tools for message development. Our methodology combines machine learning, crowdsourcing, and adaptive randomized controlled trials.
Organizations we’ve worked with
Recent academic research
Predicting Results of Social Science Experiments using Large Language Models
Luke Hewitt*, Ashwini Ashokkumar*, Isaias Ghezae, Robb Willer
(in review; contact lbh@stanford.edu for access)
Evidence of a Log Scaling Law for Political Persuasion with Large Language Models
Kobi Hackenburg, Ben Tappin, Paul Röttger, Scott Hale, Jonathan Bright, Helen Margetts
paper (preprint)
Quantifying the impact of misinformation and vaccine-skeptical content on Facebook
Jennifer Allen, Duncan Watts, David Rand
paper (Science, 2024)
How Experiments Help Campaigns Persuade Voters: Evidence from a Large Archive of Campaigns’ Own Experiments
Luke Hewitt, David Broockman, Alex Coppock, Ben Tappin, James Slezak, Valerie Coffman, Nathaniel Lubin, Mohammad Hamidian
paper (APSR, 2024)
Quantifying the potential persuasive returns to political microtargeting
Ben Tappin, Chloe Wittenberg, Luke Hewitt, Adam Berinsky, David Rand
paper (PNAS, 2023)
Using in-survey randomized controlled trials to support future pandemic response
Ben Tappin, Luke Hewitt
paper (preprint)
Contact
team@rhetorical.org
homev2CrowdvocateResearch statementTeamTemplateWork with usWhat we offerCase studiesRhetorical 2Luke HewittCVScratchHGL Supporting FiguresSPC