Skip to content

Taxonomy of EAI modalities in education

Research Method · All research methods
Evidence · 2 claims (2 for) · 2 studies (2 quant-synthesis), q3 · 1 of 2 report an effect size · 2 claims rest on one study

Description

The review organizes the educational AI literature by intervention type, finding that studies "address the potential of EAI on student performance through applications (n = 8), simulations (n = 8), VR (n = 4) and AR (n = 2)". Applications are described as contextualised to subject matter and educational level, including intelligent tutoring and games; simulations provide scenarios for discovery learning with easy access, individualisation potential and low cost; VR and AR offer immersive and manipulative learning situations. The taxonomy underpins the moderator analysis of effect sizes by AI type.

Accounts

  • Taxonomy of EAI modalities in education: applications, simulations, virtual reality and augmented reality: The review organizes the educational AI literature by intervention type, finding that studies "address the potential of EAI on student performance through applications (n = 8), simulations (n = 8), VR (n = 4) and AR (n = 2)". Applications are described as contextualised to subject matter and educational level, including intelligent tutoring and games; simulations provide scenarios for discovery learning with easy access, individualisation potential and low cost; VR and AR offer immersive and manipulative learning situations. The taxonomy underpins the moderator analysis of effect sizes by AI type. (García-Martínez et al. (2023))
  • Taxonomy of eight AI-based cognitive support types and five AI-based emotional support types in education: From 172 included articles, the review identified "eight types of AI-based cognitive support and five types of AI-based emotional support." Cognitive support types include providing individualized feedback (65 articles), real-time task guidance (45), simulating human conversations for communication skills (32), personalized learning resources (31), answering questions (26), prompting questions (13), metacognitive advice (10), and translating images/text (5). Emotional support types include tailored affective responses (34), emotional interaction without monitoring (22), reminders to relax or regulate emotions (4), instructing teachers to demonstrate empathetic behaviors (1), and grouping students with similar knowledge levels (1). This taxonomy maps the intervention space of emotional AI in education and underpins the three-category meta-analytic comparison. (Heng Zhang et al. (2025))

Claims

-

Key Sources

  • García-Martínez, I., Fernández-Batanero, J. M., Fernández-Cerero, J., & León, S. P. (2023). Analysing the Impact of Artificial Intelligence and Computational Sciences on Student Performance: Systematic Review and Meta-analysis. Journal of New Approaches in Educational Research, 12(1), 171-197. https://doi.org/10.7821/naer.2023.1.1240
  • Heng Zhang, Yuhan Liu, Meilin Jiang, Juanjuan Chen, Minhong Wang, Fred Paas. (2025). Emotional Artificial Intelligence in Education: A Systematic Review and Meta-Analysis. Educational Psychology Review. https://doi.org/10.1007/s10648-025-10086-4
Page metadata
Field Value
type research-method
id taxonomy-of-eai-modalities-in-education
title Taxonomy of EAI modalities in education
description The review organizes the educational AI literature by intervention type, finding that studies "address the potential of EAI on student performance through applications (n = 8), simulations (n = 8), VR (n = 4) and AR (n = 2)".
status review
generated by process:settle-candidates on 2026-10-15
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.