Cited by 133Artificial Intelligence in EducationIntelligent Tutoring Systems and Adaptive LearningArtificial Intelligence in Healthcare and Education

Generative AI and education: dynamic personalization of pupils’ school learning material with ChatGPT

Open access
Jauhiainen, Jussi S., Garagorry Guerra, Agustín·2024·Frontiers in Education

Abstract

The widespread use of generative AI tools like ChatGPT has seen significant growth. This rise prompted discussions on integrating these technologies into school education. However, the practical implementation, testing, and assessment of generative AI in primary and secondary education remained largely unexplored. This article examines the application of ChatGPT-3.5 and 4 in primary school education. A study involving 110 students aged 8–14 across grades 4–6 in two Uruguayan schools was conducted. The focus was on using generative AI for dynamic personalization of educational content during classroom lessons. In these sessions, instructional content followed the curriculum goals, and text, illustrations, and exercises were generated and dynamically adjusted based on generative AI. The findings indicate that generative AI effectively tailors school materials to match varying pupil knowledge levels. Real-time adjustments during lessons cater to individual learning needs, enhancing cognitive ergonomics. This approach not only boosts pupil motivation but also improves their performance, facilitating more effective achievement of the curriculum’s learning objectives. These results suggest a promising avenue for leveraging generative AI to personalize and optimize primary school education.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/feduc.2024.1288723

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Some studies integrate social-emotional and interdisciplinary tasks, where AI provides focused evaluations and follow-up recommendations that help students refine learning strategies and strengthen self-regulation.

    “Some studies also integrate social-emotional and interdisciplinary tasks, where AI provides focused evaluations and follow-up recommendations that help students refine learning strategies and strengthen self-regulation [121,129,151].”

    From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [151]

    Section 4.2 (page unavailable) describes prompt assessment of pupils’ answers and reassignment to learning materials suited to their performance; it also suggests that personalized materials may support self-regulation. But Section 3.2 describes a social-sciences history lesson, not social-emotional or interdisciplinary tasks, and the paper does not report AI giving pupils focused evaluations or follow-up recommendations to refine their learning strategies. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. Zucchermaglio, C. (1993). "Toward cognitive ergonomics of educational theory" in Designing environments for constructive learning. eds. T. Duffy, J. Lowyck and D. Jonassen (Heidelberg: Springer), 249-260.

Cited by

Sorted by citations

Authors
Jauhiainen, J. S., & Garagorry Guerra, A.
Affiliations
University of Turku (FI)
Corresponding author
Jauhiainen, Jussi S.
Venue
Frontiers in Education
Published
2024-11-19
Volume
9
ISSN
2504-284X (ISSN-L)
OpenAlex
W4404509460
Cited by
87
References
46
Citations by year
2026: 54 · 2025: 32 · 2024: 1
FWCI
32.58
Type
journal article
Language
en
Open access
Locations
  • Frontiers in Education (publishedVersion, cc-by)
  • UTUPub (University of Turku) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Turun Yliopisto
  • Business Finland
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
generative AI in education, ChatGPT, personalized learning, primary education, ChatGPT-4, student motivation, student performance, cognitive ergonomics, curriculum-based instruction, AI-generated educational content

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review