AI-BASED ADAPTIVE LEARNING IN ONLINE FOREIGN LANGUAGE EDUCATION

Authors

  • Majidov Farohiddin Independent researcher of Samarkand State Institute of Foreign Languages Author

Keywords:

adaptive learning, artificial intelligence, online language education, German as a foreign language, learner model, intelligent tutoring, CEFR, research design.

Abstract

This paper explains how artificial intelligence can make online language courses adapt to each learner, and what this means for teaching German. Only studies published between 2022 and 2026 were reviewed. Recent research shows that adaptive systems help learners: across 45 studies the average benefit was g = 0.70, and across 41 studies of AI chatbots it was 0.576. New scheduling programs that decide when a learner should review a word have also become much more accurate, cutting prediction errors by up to 64% on very large datasets. However, most of this research does not say what an adaptive program should actually track in a specific language. This paper therefore does two things. First, it shows that adaptivity is not one decision but six: choosing the next task, ordering tasks, giving feedback, planning review, placing learners at a level, and defining what can be practised. Second, it turns eight common German problems — article gender, plurals, cases after two-way prepositions, separable verbs, adjective endings, the auxiliary in the Perfekt, word order in subordinate clauses, and long compound nouns — into clear rules that a computer program can follow, each with a signal that starts extra practice and a condition that ends it. A twelve-week study with 120 learners at A2–B1 level is proposed to test these rules. The main conclusion is simple: adaptive technology only helps if it knows what is difficult in the language being taught.

References

1.X. Wang, R. T. Huang, M. Sommer, B. Pei, P. Shidfar, M. S. Rehman, A. D. Ritzhaupt, and F. Martin, “The efficacy of artificial intelligence-enabled adaptive learning systems from 2010 to 2022 on learner outcomes: A meta-analysis,” Journal of Educational Computing Research, 2024, doi: 10.1177/07356331241240459. [Online]. Available: https://journals.sagepub.com/doi/10.1177/07356331241240459

2.B. Lyu, C. Lai, and J. Guo, “Effectiveness of chatbots in improving language learning: A meta-analysis of comparative studies,” International Journal of Applied Linguistics, vol. 35, no. 2, pp. 834–851, May 2025, doi: 10.1111/ijal.12668. [Online]. Available: https://onlinelibrary.wiley.com/doi/10.1111/ijal.12668

3.M. Li, Y. Wang, and X. Yang, “Can generative AI chatbots promote second language acquisition? A meta-analysis,” Journal of Computer Assisted Learning, vol. 41, no. 4, art. e70060, Aug. 2025. [Online]. Available: https://eric.ed.gov/?id=EJ1478367

4.X.-Y. Wu, “Artificial intelligence in L2 learning: A meta-analysis of contextual, instructional, and social-emotional moderators,” System, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S0346251X2400280X

5.M. Doustizadeh and S. H. Golestaneh, “Artificial intelligence in teaching German as foreign language: Exploring the opportunities and challenges of digital educational assistants,” Critical Language and Literary Studies, vol. 22, no. 35, pp. 146–165, 2025, doi: 10.48308/clls.2025.240094.1354. [Online]. Available: https://clls.sbu.ac.ir/article_105948.html

6.N. Henry, “The effects of Processing Instruction on the acquisition and processing of grammatical gender in German,” Language Teaching Research, 2022, doi: 10.1177/13621688221096368. [Online]. Available: https://journals.sagepub.com/doi/10.1177/13621688221096368

7.D. Jach and J. Zeng, “Analysing the use of particle verbs in German as a foreign language: Unproductive particle separation and a proposal for a data-driven learning intervention,” Language Teaching Research, 2024, doi: 10.1177/13621688241300399. [Online]. Available: https://journals.sagepub.com/doi/10.1177/13621688241300399

8.A. Lorenz and E. Beyersmann, “Head-driven gender assignment in noun-noun compound recognition: Evidence from a determiner priming task in German,” PLoS One, vol. 21, no. 5, art. e0348377, 2026, doi: 10.1371/journal.pone.0348377. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC13189298/

9.A. Kříž and D. Bordag, “The role of L1 translation form in L2 compound processing: The case of native Czech speakers processing German noun-noun compounds,” Frontiers in Communication, vol. 8, art. 1133927, 2023, doi: 10.3389/fcomm.2023.1133927. [Online]. Available: https://www.frontiersin.org/journals/communication/articles/10.3389/fcomm.2023.1133927/full

10.J. Su, J. Ye, L. Nie, Y. Cao, and Y. Chen, “Optimizing spaced repetition schedule by capturing the dynamics of memory,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, pp. 10085–10097, Oct. 2023, doi: 10.1109/TKDE.2023.3251721. [Online]. Available: https://www.computer.org/csdl/journal/tk/2023/10/10059206/1LiKKhcXw52

11.Q. Xiao and J. Wang, “DRL-SRS: A deep reinforcement learning approach for optimizing spaced repetition scheduling,” Applied Sciences, vol. 14, no. 13, art. 5591, 2024, doi: 10.3390/app14135591. [Online]. Available: https://ira.lib.polyu.edu.hk/bitstream/10397/111924/1/applsci-14-05591.pdf

12.B. Ma, S. Fukui, Y. Ando, and S. Konomi, “Personalized language learning using spaced repetition scheduling,” in Artificial Intelligence in Education (AIED 2025), Lecture Notes in Computer Science, vol. 15880, Cham, Switzerland: Springer, 2025, doi: 10.1007/978-3-031-98459-4_19.

13.C. Cheng, G. Zhao, Z. Huang, Y. Zhuang, Z. Pan, Q. Liu, X. Li, and E. Chen, “Towards explainable computerized adaptive testing with large language model,” in Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 2655–2672. [Online]. Available: https://aclanthology.org/2024.findings-emnlp.149.pdf

14.“Accelerating item piloting with BERT embeddings,” in Proc. 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA), 2024. [Online]. Available: https://aclanthology.org/2024.bea-1.35.pdf

15.B. Şimşek, B. Direkci, B. Koparan, S. Akbulut, E. E. Şimşek, M. Gülmez, and D. N. Ökmen, “Artificial intelligence-assisted vocabulary teaching: A meta-analysis study,” Frontiers in Artificial Intelligence, vol. 9, art. 1806700, 2026, doi: 10.3389/frai.2026.1806700. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC13149277/

16.Y. Zhou and M. Zhou, “A meta-analysis on mobile-assisted vocabulary learning: Do mobile applications help?,” ReCALL, 2025, doi: 10.1017/S0958344025100335. [Online]. Available: https://www.cambridge.org/core/journals/recall/article/79C8F00E48D521ED3BCFE0625B5549F3

17.“A systematic review of AI-driven intelligent tutoring systems (ITS) in K-12 education,” npj Science of Learning, 2025. [Online]. Available: https://www.nature.com/articles/s41539-025-00320-7

18.Goethe-Institut, “Goethe-Test PRO: German for professionals.” [Online]. Available: https://www.goethe.de/ins/se/en/spr/prf/bulats.cfm (accessed Sep. 5, 2026).

19.C. Freeman, A. Kittredge, H. Wilson, and B. Pajak, “The Duolingo method for app-based teaching and learning,” Duolingo Research Report, Jan. 2023. [Online]. Available: https://duolingo-papers.s3.amazonaws.com/reports/Duolingo_whitepaper_duolingo_method_2023.pd

20.H. Huang and Y. Li, “Zum Nachfelderwerb im Schriftdeutschen bei chinesischen Deutschlernenden: Eine korpusgestützte longitudinale Untersuchung,” Korpora Deutsch als Fremdsprache (KorDaF), 2024. [Online]. Available: https://kordaf.tujournals.ulb.tu-darmstadt.de/article/id/4145/

21.Goethe-Institut, “German exams A1–C2.” [Online]. Available: https://www.goethe.de/en/spr/prf.html (accessed Sep. 5, 2026).

Downloads

Published

2026-05-30