Persuasion Through AI-Enhanced Communication

Last registered on October 13, 2025
View Trial History

Pre-Trial

Trial Information

General Information

Title
Persuasion Through AI-Enhanced Communication
RCT ID
AEARCTR-0016988
Initial registration date
October 09, 2025

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
October 13, 2025, 11:00 AM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Name
Kristian López Vargas
Affiliation
University of California, Santa Cruz
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Gonzalo Respighi Grasso
PI Affiliation
UC Santa Cruz
Contact Investigator
PI Name
Julian Martinez Iriarte
PI Affiliation
UC Santa Cruz
Contact Investigator
PI Name
Valerie Dube
PI Affiliation
Carnegie Mellon U
Contact Investigator

Additional Trial Information

Status
On going
Start date
2025-10-09
End date
2026-10-09
Keywords
Behavior, Lab
Additional Keywords
Artificial Intelligence; AI-assisted communication; Experimental economics; Dictator game; Persuasion; Generosity / altruism
JEL code(s)
C91, D03, O33
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
This laboratory experiment investigates how communication—both human and AI-assisted—affects generosity in the dictator game. In the baseline condition, Player A (the dictator) decides how much money to share with Player B (the recipient) without any communication. In a second condition, Player B can write a message to Player A before the decision. In the third condition, Player B can use an AI chatbot to help craft that message. By comparing outcomes across these conditions, the study explores whether access to AI tools enhances persuasive communication and increases altruistic behavior.
External Link(s)

Registration Citation

Citation
Dube, Valerie et al. 2025. "Persuasion Through AI-Enhanced Communication." AEA RCT Registry. October 13. https://doi.org/10.1257/rct.16988-1.0
Sponsors & Partners
Experimental Details

Interventions

Intervention(s)
Participants are recruited on Prolific to play a one-shot Dictator Game (DG) online. Each participant is assigned a fixed role (Dictator = Player A; Receiver = Player B) for the entire session. We implement three pre-decision communication conditions:
T1 — No communication (baseline): A decides the allocation with no message from B.
T2 — Human message: Before A’s decision, B can send one short message. Messages must be non-identifying and non-offensive; they are shown verbatim to A.
T3 — AI-assisted message: Before A’s decision, B can draft a message using an embedded LLM assistant. B edits and chooses the final text to send.
The interface enforces length/content constraints and records the final message and any AI interaction metadata (e.g., whether the assistant was opened).
Intervention Start Date
2025-10-09
Intervention End Date
2026-01-09

Primary Outcomes

Primary Outcomes (end points)
The primary outcome is the amount transferred by Player A (the dictator) to Player B (the recipient) in the dictator game. This captures generosity or altruism under different communication conditions.
Primary Outcomes (explanation)
The primary outcome is the amount transferred by Player A (the dictator) to Player B (the recipient) in the dictator game. This captures generosity or altruism under different communication conditions.

Secondary Outcomes

Secondary Outcomes (end points)
Secondary outcomes involve text-based analysis of messages written under different conditions, focusing on linguistic features, tone, structure, and content differences across human-written and AI-assisted messages.
Secondary Outcomes (explanation)
Secondary outcomes involve text-based analysis of messages written under different conditions, focusing on linguistic features, tone, structure, and content differences across human-written and AI-assisted messages.

Experimental Design

Experimental Design
We use a within-subjects, block-randomized design. Each participant experiences all three treatment conditions in three blocks; block order is randomized at the session level. Within each block, there are multiple independent rounds with random, anonymous rematching in every round. Roles are fixed across blocks/rounds.
Unit of analysis (primary): Individual decision makers.
Compliance: In T2/T3, Player B may choose to send nothing; we define intent-to-treat (ITT) by assigned block and possibly report contrasts restricted to rounds in which a message was sent.

Sample size (plan): 360 participants total (balanced between Player As and Player Bs), all exposed to all three blocks.
180 in each role. Each interacts in 12 rounds (4 for each block/treatment). That is, 2,160 observations (720 observations for treatment).

Randomization: computer-implemented; block order randomized; matchings randomized each round.
Blinding: Participants only see counterpart’s role (and any standard, non-identifying info if used).
Experimental Design Details
Not available
Randomization Method
Randomization: computer-implemented; block order randomized; matchings randomized each round.
Randomization Unit
Randomization: computer-implemented; block order randomized; matchings randomized each round.
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
360 participants total (balanced between Player As and Player Bs), all subjects will be exposed to all three treatments (in random order).

180 participants in each role, Player A and Player B.
Sample size: planned number of observations
360 participants total (balanced between Player As and Player Bs), all subjects will be exposed to all three treatments (in random order). 180 participants in each role, Player A and Player B. Each participant interacts in 12 rounds (4 rounds per block/treatment). That is, 180*12 = 2,160 observations Since we have three treatments, we have: 2,160 /3 = 720 observations per treatment.
Sample size (or number of clusters) by treatment arms
It is a within-subject design. All participants experience all treatments. We will have 180 clusters (participants) in each role.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
UC Santa Cruz Office of Research Compliance Administration (ORCA)
IRB Approval Date
2024-05-30
IRB Approval Number
HS-FY2024-262
Analysis Plan

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information