Rhetorical Labs

image

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.

Research statement What we offer

Organizations we’ve worked with

image
image
image
image
image
image
image
image

Recent academic research

image

Predicting Results of Social Science Experiments using Large Language Models

Luke Hewitt*, Ashwini Ashokkumar*, Isaias Ghezae, Robb Willer

paper (preprint)

image

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)

image

Using survey experiment pre-testing to support future pandemic response

Ben Tappin, Luke Hewitt

paper (PNAS Nexus, 2024)

image

Quantifying the impact of misinformation and vaccine-skeptical content on Facebook

Jennifer Allen, Duncan Watts, David Rand

paper (Science, 2024)

image

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)

image

Quantifying the potential persuasive returns to political microtargeting

Ben Tappin, Chloe Wittenberg, Luke Hewitt, Adam Berinsky, David Rand

paper (PNAS, 2023)

Contact

team@rhetorical.org

homev2CrowdvocateResearch statementTeamTemplateWork with usWhat we offerCase studiesRhetorical 2Luke HewittCV
ScratchHGL Supporting Figures