CoChat

Arapça Öğretiminde Yapay Zekâ’nın Rolü: Chatgpt Örneği

Open access
Yıldırım, Tahsin · 2025 · Mizanü'l-Hak: İslami İlimler Dergisi

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index; 1 of the 15 sources its claims cite were checked for support.

Abstract

Bu makale, yapay zekâ teknolojilerinin yabancı dil öğrenimindeki etkisini detaylı bir şekilde incelemektedir. Özellikle ChatGPT ve diğer yapay zekâ tabanlı dil öğrenme araçlarının, Türkçe konuşan bireylerin Arapça öğrenme süreçlerinde nasıl etkili bir rol oynayabileceği ele alınmıştır. Çalışmada, Arapça öğrenenlerin en çok zorlandığı alanlar olan diyalog kurma, kelime ve cümle anlamı, metin çevirisi, telaffuz, okuma pratiği ve geri bildirim alma gibi unsurlar üzerinde durulmuştur. Yapay zekâ araçlarının, bu alanlarda sunduğu bireyselleştirilmiş geri bildirimler ile öğrencilerin öğrenme süreçlerini daha etkili hale getirdiği ortaya konulmuştur. Aynı zamanda yapay zekânın, dil öğrenim sürecini kişiselleştirme yeteneği sayesinde her öğrencinin kendi hızında ve ihtiyacına göre dil öğrenme deneyimi yaşadığı vurgulanmıştır. Çalışmanın sonuçlarına göre, yapay zekâ tabanlı araçlar, öğrenicilerin dil hatalarını en aza indirgemekte, dil becerilerini geliştirmekte ve öğrenme sürecini hızlandırmaktadır. Sonuç olarak, ChatGPT ve benzeri yapay zekâ tabanlı dil öğrenme araçlarının, dil öğrenme sürecinde verimliliği artırdığı ve yabancı dil öğrenimini daha kolay ve etkili hale getirebileceği sonucuna ulaşılmıştır.

Overview

CoChat Summary

TL;DR

This qualitative case study examines ChatGPT’s role in teaching Arabic to Turkish speakers, using CEFR-based examples across dialogue, vocabulary, translation, pronunciation, reading, feedback, grammar explanation, and test preparation. It finds ChatGPT can provide useful personalized practice and correction but has limitations in level appropriateness, semantic feedback, test accuracy, and technical terminology, requiring teacher guidance.

Key findings

  • ChatGPT supported Arabic learning in 12 application areas described in the text, including dialogue, word/sentence meaning, Turkish–Arabic translation, pronunciation, reading practice, written feedback, grammar explanation, and test preparation.
  • It often gave correct translations and corrections, such as fixing the learner’s “bil-ghurbu” to “bil-ghurba” and identifying a tense mismatch between “أمس” and “سأكل”; it also produced a 5-question B1-level test with answer key.
  • Limitations included producing Arabic without harakat unless prompted, using English characters for Turkish pronunciation, giving answers often aimed at intermediate/advanced rather than beginner levels, and making errors in test answer keys and classical-text terminology.
  • The paper concludes ChatGPT cannot replace the teacher but can enrich learning when used under teacher guidance and with continuous updates.

Methods

  • Qualitative case study (“durum çalışması modeli”) on ChatGPT’s use in teaching Arabic as a foreign language to Turkish speakers.
  • Data consisted of ChatGPT interactions and outputs across the application areas listed in the text, evaluated against the CEFR 2021 language scales and the Arabic Preparatory Program’s B1 target level.
  • Analysis was qualitative evaluation of the dialogues, translations, feedback, and exercises; no quantitative sample, statistical test, or learner-outcome measurement is reported.

Limitations

  • The paper states that ChatGPT’s responses often target intermediate and advanced levels, may not detect semantic errors, can contain errors in test answer keys, and makes terminological mistakes in translating classical Arabic texts.
  • The paper also lists ChatGPT’s own stated limitations: information can be wrong and needs verification, it may produce harmful or biased content, its knowledge after 2021 is limited, it writes Arabic without harakat unless prompted, and it uses English characters for Turkish pronunciation.
  • Evident from the text: the study is a single qualitative evaluation of ChatGPT examples rather than a controlled study with participants, pre/post measurement, or generalizable learner outcomes.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.47502/mizan.1620616

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

1 Valid · 15 Not valid · 14 Not checked · 54 Own results and interpretations

8 more claims

Create a free account to see all 84 claims and to verify the 7 references still open.

See all claims — free account
  • It may state two separate claims as one. 28
  • Probably not a substantial claim. 55
  • The quote only partly states this claim. 3

Create a free account to see these claims.

Self-check

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

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 15 references

Research works printed but not linked: 8

  1. Gürlek, Yakup vd. "Yapay Zekanın Eğitime Etkileri Ve Uygulamaları". International Journal of Original Educational Research 1/1 (2023), 25-132.
  2. Yakup Gürlek vd., "Yapay Zekanın Eğitime Etkileri Ve Uygulamaları", International Journal of Original Educational Research 1/1 (2023), 130.
  3. Kurnaz, Ahmet vd. "Öğretmenlerin uzaktan eğitime ilişkin görüşleri". Milli Eğitim Dergisi 49/1 (2020), 293-322.
  4. Murat Özcan, "Türkiye'de ve Dünyada Arapça Öğretimi için Müfredat Geliştirme Çalışmaları ve İlköğretim Arapça Dersi Müfredatı için Bazı Öneriler", International journal of Science Culture and Sport 3/12 (01 Ocak 2015), 84.
  5. Özcan, Murat. "Türkiye'de ve Dünyada Arapça Öğretimi için Müfredat Geliştirme Çalışmaları ve İlköğretim Arapça Dersi Müfredatı için Bazı Öneriler". International journal of Science Culture and Sport 3/12 (01 Ocak 2015), 81-81. https://doi.org/10.14486/IJSCS361 · DOI · Paper page
  6. Mustafa Seyrek vd., "Öğretmenlerin Eğitimde Yapay Zeka Kullanımına Yönelik Algıları", International Journal of Social and Humanities Sciences Research (JSHSR) 11/106 (2024), 851;
  7. Vornachev, Andrii vd. "Is Artificial Intelligence a Utopia or the Future of Foreign Language Learning". https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4917981
  8. Yücel, Mukadder Seyhan. "Avrupa Ortak Başvuru Metni -Avrupa Dil Portföyü Eleştirel Bir Yaklaşım". Trakya Üniversitesi Sosyal Bilimler Dergisi 8/1 (2006), 110-122. "ARA2001-18V1S1-10-0-1-SV1-ebook.pdf". Erişim 21 Eylül 2024. https://ets.anadolu.edu.tr/storage/nfs/ARA2001/ebook/ARA2001-18V1S1- 10-0-1-SV1-ebook.pdf "Introducing ChatGPT". Erişim 22 Eylül 2024. https://openai.com/index/chatgpt/ Elektronik Kaynaklar (1) https://CHATGPT.com/share/66f2d5e0-8afc-8001-bcff-0a6d683a2de1/ adresinden 24 Eylül 2024 tarihinde alınmıştır.

Metadata

Authors
Yıldırım, T.
Affiliations
Izmir Kâtip Çelebi University (TR)
Corresponding author
Yıldırım, Tahsin
Venue
Mizanü'l-Hak: İslami İlimler Dergisi
Published
2025-06-30
Issue
20
Pages
299-322
ISSN
2149-9896 (ISSN-L)
OpenAlex
W4411966031
Cited by
4
References
15
Citations by year
2026: 4
FWCI
1.61
Type
journal article
Language
tr
Open access
Locations
Mizanü l-Hak İslami İlimler Dergisi (publishedVersion)
Topics
  • Social Sciences › Education › Artificial Intelligence in Education
  • Social Sciences › Education › Arabic Language Education Studies
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
Arabic language teaching, ChatGPT, AI-assisted language learning, Arabic as a foreign language, personalized feedback, conversation skills, translation, pronunciation, reading practices, student errors, personalized learning

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-11-16, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-16 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash).

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Arapça Öğretiminde Yapay Zekâ’nın Rolü: Chatgpt Örneği. https://app.cochat.ai/papers/10.47502/mizan.1620616
The paper
Yıldırım, T. (2025). Arapça Öğretiminde Yapay Zekâ’nın Rolü: Chatgpt Örneği. Mizanü'l-Hak: İslami İlimler Dergisi. https://doi.org/10.47502/mizan.1620616

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.