Correcting Asymmetry of Information: How AI Persona Design Shapes Higher Education Enrollment Intentions

How to cite

Polanco-Jimenez, Jaime; Witte, Kristof De; François, Maxime. 2026. "Correcting Asymmetry of Information: How AI Persona Design Shapes Higher Education Enrollment Intentions." AEA RCT Registry. AEARCTR-0019117. https://doi.org/10.1257/rct.19117-1.1

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

Jaime Polanco-Jimenez* , Kristof De Witte , Maxime François

* Primary investigator

Registry ID
AEARCTR-0019117
DOI
https://doi.org/10.1257/rct.19117-1.1
First registered
Last updated
Status
In development
Trial dates
2026-06-01 – 2027-06-30
Countries
Private
JEL codes
I21, I24, J15, C93, D83, D91
Registry record
http://www.socialscienceregistry.org/trials/19117

Abstract

From an economic perspective, human capital investment decisions are driven by a comparison of expected lifetime benefits and costs. When information is asymmetric — as is particularly acute for students from migrant and lower socioeconomic backgrounds, but not exclusive to them — subjective expectations deviate from objective returns: families tend to overestimate the direct and indirect costs of higher education (tuition, living expenses, opportunity cost) and underestimate its long-term benefits (wage premiums, employment stability). This informational wedge can flip the Human Capital Model's investment inequality, producing suboptimal non-enrollment among individuals who would experience positive net returns from tertiary education.

This study implements a five-armed randomized controlled trial to test whether an AI chatbot can correct this informational wedge and increase secondary school students' intention to enroll in higher education. We randomly assign individual participants to one of four treatment arms — each delivering identical educational information through a distinct conversational persona designed to target a specific information friction (factual correction of cost-benefit misperceptions, positive affect priming, psychological scaffolding of self-efficacy beliefs, or narrative persuasion via near-peer role models) — or to a placebo control arm in which the AI discusses an unrelated topic (summer activities). This design enables us to (a) isolate the causal effect of AI-delivered educational information from the mere effect of interacting with an AI, (b) identify which communication framing is most effective at correcting the informational wedge, and (c) test whether treatment effects are moderated by students' time preferences, which theory predicts should interact with the cognitive load imposed by different persona designs. This study replicates and extends an initial trial conducted in Flanders, Belgium (AEARCTR-0017212; N = 163, 4 arms), with the addition of a placebo control arm and deployment across six European countries to strengthen external validity.

Intervention

The intervention consists of a structured interaction with an AI-driven educational chatbot ("Academic Pathway Assistant," powered by Google Gemini via Vertex AI) designed to assist secondary school students, with a particular focus on those from migrant backgrounds. Participants are randomly assigned to one of five groups, each targeting a specific dimension of the informational wedge:

Arm 1 — Neutral/Factual (Active Control). A purely factual, reactive information assistant that delivers country-specific higher education facts without emotional framing. Directly targets the informational wedge at its root by correcting misperceptions about costs, pathways, and returns. Tone: polite, concise, and direct. No emojis, chitchat, or emotional validation. Closes with: "Does this answer your question?"

Arm 2 — Engaging/Enthusiastic (Treatment 1). A high-energy student ambassador presenting the same factual information framed as exciting discoveries ("Did you know?"). Designed to lower the psychological cost of the interaction and prevent attention-driven attrition. Uses exclamation points, emojis, and opportunity framing. Closes with an upbeat question about interests.

Arm 3 — Empathetic/Supportive (Treatment 2). A reassuring educational counselor that validates the student's emotions and anxieties before providing factual information. Each response begins with approximately two sentences of emotional support, then presents country-specific facts. Closes with: "How does that make you feel?"

Arm 4 — Relatable Mentor/Storyteller (Treatment 3). A near-peer mentor (older student persona) wrapping factual information in brief micro-stories about a "friend" or peer. May invent peer names and emotions but must not invent institutional details (e.g., grant amounts, deadlines). The story's resolution must be a real, country-specific fact. Closes with a connection-building question.

Arm 5 — Summer Activities (Placebo Control). A friendly summer activities guide discussing fun and interesting leisure activities specific to the student's country (outdoor activities, festivals, cultural events, local traditions, travel, sports, seasonal hobbies). This arm deliberately excludes all higher education content. It retains identical conversational flow constraints (response length, language matching, variation rules) but does not receive the educational knowledge base.

Experimental design

This is a five-armed between-subjects Randomized Controlled Trial (RCT) grounded in the Human Capital Model under information asymmetry. It replicates and extends AEARCTR-0017212 with a placebo control arm and pre-registered hypotheses. Participating individuals from schools and NGOs are randomly assigned to one of five experimental groups:

1. Arm 1 — Neutral/Factual (Active Control): factual information assistant targeting the informational wedge through rational persuasion.
2. Arm 2 — Engaging/Enthusiastic (Treatment 1): enthusiastic guide testing positive affect priming and cognitive search cost reduction.
3. Arm 3 — Empathetic/Supportive (Treatment 2): empathetic counselor targeting self-efficacy via psychological scaffolding.
4. Arm 4 — Relatable Mentor/Storyteller (Treatment 3): near-peer mentor targeting underestimated benefits via narrative persuasion.
5. Arm 5 — Summer Activities (Placebo Control): leisure conversation guide isolating the effect of information provision from AI interaction.

Data is collected via pre- and post-interaction surveys embedded in the chat application. The post-test is triggered after a minimum of 30 conversational turns. All chat messages (user and bot) are logged with timestamps.

Design details

Randomization method
Computerized randomization using client-side stratified block randomization. Within each country stratum, participants are assigned using balanced permuted blocks of size 5, guaranteeing equal allocation across all five arms within every 5 consecutive participants per country.
Randomization unit
Individual (stratified by country).
Clusters
Not applicable (individual-level randomization, stratified by country).
Observations
525 students (105/arm), derived from d = 0.50 (medium), inflated for 40% attrition.
Arms
105 participants per arm
Primary outcomes
Intention to Enroll in Higher Education.
Secondary outcomes
1. Academic Self-Efficacy 2. Revealed Preference (Information Seeking) 3. Future Planning Concreteness 4. Perceived AI Core Style (Manipulation Check) 5. AI Trust and Perceived Helpfulness 6. Behavioral Engagement (Attrition and Interaction Intensity) 7. Conversational Engagement Depth

Cited by

No citation data available for this registration yet.

Keywords