AI Tutors vs. Tenacious Myths: Evidence from Personalised Dialogue Interventions in Education

TL;DR

This study shows that personalized AI dialogue can effectively reduce stubborn misconceptions in education through interactive engagement, with effects lasting longer than traditional methods but requiring reinforcement for sustained change.

Contribution

It provides evidence that personalized AI dialogue outperforms generic refutations in correcting misconceptions and enhances engagement and confidence in learners.

Findings

Personalized AI dialogue significantly reduces misconceptions immediately.

Effects of AI dialogue persist at 10-day follow-up but diminish by 2 months.

AI dialogue increases engagement and confidence compared to textbook reading.

Abstract

Misconceptions in psychology and education persist despite clear contradictory evidence, resisting traditional correction methods. This study investigated whether personalised AI dialogue could effectively correct these stubborn beliefs. In a preregistered experiment (N = 375), participants holding strong psychology misconceptions engaged in one of three interventions: (1) personalised AI dialogue targeting their specific misconception, (2) generic textbook-style refutation, or (3) neutral AI dialogue (control). Results showed that personalised AI dialogue produced significantly larger immediate belief reductions compared to both textbook reading and neutral dialogue. This advantage persisted at 10-day follow-up but diminished by 2 months, where AI dialogue and textbook conditions converged while both remained superior to control. Both AI conditions generated significantly higher engagement and confidence than textbook reading, demonstrating the motivational benefits of conversational interaction. These findings demonstrate that AI dialogue can accelerate initial belief correction through personalised, interactive engagement that disrupts the cognitive processes maintaining misconceptions. However, the convergence of effects over time suggests brief interventions require reinforcement for lasting change. Future applications should integrate AI tutoring into structured educational programs with spaced reinforcement to sustain the initial advantages of personalised dialogue.