The Persuasive Power of Multi-Modal AI: A Randomized Controlled Trial of Microtargeting Effectiveness

How to cite

Ali, Ayesha; Qazi, Ihsan Ayyub; Qazi, Zafar Ayyub. 2025. "The Persuasive Power of Multi-Modal AI: A Randomized Controlled Trial of Microtargeting Effectiveness." AEA RCT Registry. AEARCTR-0015650. https://doi.org/10.1257/rct.15650-1.0

Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.

Ayesha Ali* , Ihsan Ayyub Qazi , Zafar Ayyub Qazi

* Primary investigator

Registry ID
AEARCTR-0015650
DOI
https://doi.org/10.1257/rct.15650-1.0
First registered
Last updated
Status
In development
Trial dates
2024-09-19 – 2025-07-31
Countries
Private
Registry record
http://www.socialscienceregistry.org/trials/15650

Abstract

This study evaluates the persuasive effects of microtargeted persuasion campaigns generated using multi-modal large language models (LLMs) using a Randomized Controlled Trial (RCT) conducted in Lahore, Pakistan. By examining the efficacy of AI-driven personalization in a Global South context, this research aims to contribute to our understanding of emerging technological applications in political communication and public engagement strategies.

Experimental design

We will conduct a stratified RCT (using high and low digital literacy samples), where each participant in the strata will be assigned to either the control or treatment group with equal probability. For each of our three topics, both the treatment and control groups will be shown three videos in a randomized order. The treatment group will receive microtargeted AI-generated videos designed to persuade the participants in a particular direction. The control group will be shown unrelated placebo videos. We will measure participants view on topics issue pre and post treatment/placebo implementation to capture any persuasion effects.

Design details

Randomization method
done in office by a computer
Randomization unit
individual
Clusters
200
Observations
200
Arms
100
Primary outcomes
Persuasion effects

Cited by

No citation data available for this registration yet.

Keywords