CoChat
Sign Up
Cited by 13Reading and Literacy DevelopmentArtificial Intelligence in EducationIntelligent Tutoring Systems and Adaptive Learning

ChatGPT enhances reading comprehension for children with dyslexia in Arabic language

Gharaibeh, Mahmoud, Basulayyim, Abdullah·2025·Disability and Rehabilitation: Assistive Technology
DOI 10.1080/17483107.2025.2508389
Open this paper in CoChat — free account

Abstract

PURPOSE: The study investigated the impact of ChatGPT, an AI language model, on enhancing reading comprehension skills among Arabic-speaking children with dyslexia. MATERIALS AND METHODS: The study population consisted of 60 Arabic-speaking children with dyslexia, aged 8 to 11 years, selected from public and private schools in the United Arab Emirates (UAE). A quasi-experimental design was adopted, with participants divided into control and experimental groups. The experimental group received ChatGPT-based reading instruction during regular school hours. Data was collected using the Sentence Reading Comprehension Test and the Reading Maze Test. The pre- and post-tests were administered to both groups, with equivalent reading difficulty but different texts. RESULTS: The findings of the study revealed a significant improvement in reading comprehension scores among the experimental group compared to the control group. Specifically, the post-test scores showed increased sentence comprehension accuracy and better contextual understanding of reading materials. CONCLUSIONS: Based on these findings, it is recommended that AI tools like ChatGPT be integrated into remedial reading programs for children with dyslexia. Educators should consider leveraging AI-assisted reading exercises to provide personalized learning experiences that can support and accelerate reading development in struggling learners.

Integrity signals

Registry

Crossref · 10.1080/17483107.2025.2508389

Cites

63 of 63 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • GenAI was employed to deliver personalized and leveled reading materials, helping to reduce obstacles such as comprehension difficulties, anxiety, or lack of confidence resulting from cognitive differences among students.

    “GenAI was employed to deliver personalized and leveled reading materials, helping to reduce obstacles such as comprehension difficulties, anxiety, or lack of confidence resulting from cognitive differences among students [75-80].”

    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 [75]

  • Across writing, reading, and mathematics tasks, students repeatedly submit work to AI systems, receive concrete suggestions, and resubmit revised work, creating a cycle of practice, feedback, and renewed practice.

    “Across writing, reading, and mathematics tasks, students repeatedly submit texts, assignments, or answers to AI systems, receive concrete suggestions on error correction, structure, and language use, and then resubmit revised work, creating a cycle of practice, feedback, and renewed practice [75,77,82,83,87,90,110].”

    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 [75]

  • Evidence spans STEM and the humanities, including gains in understanding physics and programming, as well as improved reading and poetry interpretation.

    “Evidence spans STEM and the humanities, including gains in understanding physics [91,101,104,147] and programming [95,148,150], as well as improved reading and poetry interpretation [72,75,81,116].”

    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 [75]

Cites

Flagged first, then by citations

Research works printed but not linked: 6

  1. 10.33499/edren.v12i1.3866 · DOI
  2. 10.3233/ben-2012-119004 · DOI
  3. Hashim S, Omar MK, Ab Jalil H, et al. Trends on technologies and artificial intelligence in education for personalized learning: systematic literature. J Acad Res Progr Educ Develop. 2022;12(1):884–903.
  4. Kawther G Kawther T. ChatGPT in the New Teaching/Learning Era Operating as a Bliss or Curse. Master’s Thesis Guelma Algeria University of Guelma; 2024. http://dspace.univ-guelma.dz/jspui/handle/123456789/16759
  5. Khomsi A. Epreuve d’évaluation de la compétence en lecture: lecture de mots et compréhension-révisée. Algiers, Algeria: Les Editions du Centre de psychologie appliquée; 1999.
  6. Nacheva R, Czaplewski M. Artificial intelligence in helping people with disabilities: opportunities and challenges. HR Technolog. 2024;1(1):102–124.

Cited by

Sorted by citations

Related

Authors
Gharaibeh, M., & Basulayyim, A.
Affiliations
  • Al Ain University (AE)
  • King Abdulaziz University (SA)
Corresponding author
Gharaibeh, Mahmoud
ORCID
Venue
Disability and Rehabilitation: Assistive Technology
Publisher
Informa UK Limited
Published
2025-05-21
Volume
20
Issue
8
Pages
2858-2871
ISSN
  • 1748-3107 (ISSN-L)
  • 1748-3115
DOI
10.1080/17483107.2025.2508389
OpenAlex
W4410559854
Cited by
13
References
63
Citations by year
2026: 8 · 2025: 5
FWCI
14.29
Type
journal article
Language
en
Open access
closed
Locations
  • Disability and Rehabilitation Assistive Technology (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Social Sciences › Psychology › Developmental and Educational Psychology › Reading and Literacy Development
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
ChatGPT, dyslexia, reading comprehension, Arabic-speaking children, remedial reading programs, sentence comprehension, contextual understanding, personalized learning, reading development
MeSH terms
Generative Artificial Intelligence, Child, Dyslexia, Female, Humans, Language, Male, Reading, United Arab Emirates, Comprehension

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