A Differential Analysis of Artificial Intelligence Capabilities in Assessing the Three Primary Skills of Persian Language Based on the Saadi Foundation’s Reference Standard Relative to the Speaking Domain

Document Type : Research Paper

Authors

1 Assistant Professor and Instructor at the Center for Language and Islamic Studies Teaching of Al-Mustafa International University

2 Persian Language Instructor at Al-Mustafa International University

Abstract

Abstract

This study employs a discrepancy analysis approach to compare the theoretical capabilities of Artificial Intelligence (AI) in assessing reading, writing, and listening skills against the descriptors of the Saadi Foundation's "Reference Standard for Persian Language Education." Utilizing a critical documentary analysis method and a three-dimensional analytical matrix (including indicators of machine-processability, context-dependency, and inference robustness), 36 skill descriptors were examined. The findings revealed a pattern of "asymmetric validity distribution." AI showed the highest alignment in assessing reading skills due to the static nature of text. In writing assessment, the "correct form versus invalid content" contradiction (AI hallucination) and the inability to evaluate discourse logic reduced validity at advanced levels. For listening, a profound gap was observed between audio decoding and the inference of layered meaning (e.g., tone, irony). The discrepancy analysis indicates that the gaps in the three skills are primarily epistemological and concentrated at advanced levels (C1-C2), whereas in speaking (as a comparative reference point), the gap is interactional-situational and begins at intermediate levels. Consequently, complete reliance on AI for comprehensive Persian language assessment, especially at advanced levels, risks reducing communicative competence and threatening construct validity. Accordingly, a "Hierarchical Skill-Based Hybrid Assessment Model" is proposed, in which AI's role is modulated from an exclusive assessor at basic levels to an auxiliary tool under human supervision at advanced levels.

Keywords: Automated Language Assessment, Artificial Intelligence, Saadi Foundation Reference Standard, Validity Discrepancy Analysis, Hybrid Assessment Model

Keywords

Main Subjects

References

  • ابراهیمی، مجتبی، طالعی ، محمد حسین،(1404) ، شکاف سنجش گفتار در زبان فارسی: واکاوی تطبیقی قابلیت های هوش مصنوعی و استاندارد مرجع بنیاد سعدی، دوفصلنامه مطالعات بین المللی آموزش زبان فارسی، شماره( 20)
  • استاجی، معصومه.، صحرایی، رضا مراد.، و شهباز، منیره. (۱۴۰۳). ارزیابی روانی گفتار آزمون‌دهندگان فارسی‌آموز خارجی: نقش تکرار و خطای شروع در سطوح مختلف بسندگی زبان فارسی. فصلنامه اندازه‌گیری تربیتی،۱۵،56، ۶۹-۱۰۲.  https://doi.org/10.22054/jem.2024.73106.3454
  • اسمی، مهدی و برومند تمبکی، شهداد. (1403). بررسی تاثیر هوش مصنوعی (AI) بر یادگیری مهارت های زبانی در آموزش آنلاین.اولین کنفرانس بین المللی مطالعاتکاربردی در فرایندهای تعلیم و تربیت، بندرعباس. https://civilica.com/doc/2247368
  • صبوری، سپهر.، و حاج ملک، محمد مهدی، (1402). استفاده از ظرفیت‌های هوش مصنوعی در آموزش تلفظ زبان‌های خارجی. نهمین کنفرانس بین‌المللی وب پژوهی.
  • صحرایی، مراد رضا و همکاران، (1395)، استاندارد مرجع بنیاد سعدی.
  • قاسمی، مهدی و برومند تمبکی، شهداد. (1403). بررسی تاثیر هوش مصنوعی (AI) بر یادگیری مهارت های زبانی در آموزش آنلاین. اولین کنفرانس بین المللی مطالعات کاربردی در فرایندهای تعلیم و تربیت، بندرعباس. https://civilica.com/doc/2247368
  • Acosta-Rivera, L. G., & Bedón Vaca, C. d. C. (2025). Impacto de la inteligencia artificial en el aprendizaje del inglés como lengua extranjera en estudiantes de bachillerato en Ecuador. Revista RedCA, 8(22). https://doi.org/10.36677/redca.v8i22.26361
  • Aryadoust, V., Zakaria, A., Lim, M. H., & Chen, C. (2021). An extensive knowledge mapping review of measurement and validity in language assessment and SLA research. Frontiers in Psychology, 11, 1941. https://doi.org/10.3389/fpsyg.2020.01941
  • Bender, E. M., & Koller, A. (2020). Climbing towards NLU: On meaning, form, and understanding in the age of data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 5185–5198). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.ACL-MAIN.463
  • Cicchetti, Domenic. (1994). Guidelines, Criteria, and Rules of Thumb for Evaluating Normed and Standardized Assessment Instruments in Psychology. Psychological Assessment. 6. 284-290. 10.1037/1040-3590.6.4.284.
  • Chapelle, C. A., & Voss, E. (Eds.). (2021). Validity argument in language testing: Case studies of validation research. Cambridge University Press. https://assets.cambridge.org/97811084/84022/frontmatter/9781108484022_frontmatter.pdf
  • Dakhil, T. A., Karimi, F., Al-Jashami, R. A. U., & Ghabanchi, Z. G. (2025).[1][2][3] The effect of artificial intelligence (AI)-mediated speaking assessment on speaking performance and willingness to communicate of Iraqi EFL learners. International Journal of Language Testing, 15(2), 1-18.[1][2] 22034/ijlt.2024.486564.1383
  • Fakhrurriana, R., & Herdina, G. F. (2024). Assessment test of receptive skills: Listening and reading comprehension of recount text using AI platform (Atomic Learning). International Conference on Religion, Spirituality and Education (ICRSE), 3, 211-218. [https://sunankalijaga.org/prosiding/index.php/icrse/article/view/1244]
  • Gomede, E. (2024, March 27). Decoding the unspoken: Advancements in pragmatic analysis within natural language processing. The Modern Scientist. https://medium.com/the-modern-scientist/decoding-the-unspoken-advancements-in-pragmatic-analysis-within-natural-language-processing-d6358775a099
  • Grab, M. O. (2025). Strategies for integrating Artificial Intelligence (AI) to improve and assess English oral communication skills. International Journal of Research in Education and Science, 11(3), 533-552. https://eric.ed.gov/?id=EJ1480918
  • Hınız, G. (2026). Using AI to enhance receptive foreign language skills. In AI's Role in Language Learning and Communication (pp. 36-71). IGI Global. https://doi.org/10.4018/979-8-3373-5681-5.ch003
  • Huth, T. (2020). Testing interactional competence: Patterned yet dynamic aspects of L2 interaction. Papers in Language Testing and Assessment, 9(1), 1–25.
  • Likert, R. (1932). A technique for the measurement of attitudes. The Science Press. (Archives of Psychology, No. 140)
  • Ie, X., & Jaeger, T. F. (2020). Comparing non-native and native speech: Are L2 productions more variable? The Journal of the Acoustical Society of America, 147(5), 3322–3347. https://doi.org/10.1121/10.0001141
  • Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), 1–38. https://doi.org/10.1145/3571730
  • Kane, M. T. (2013). Validating the interpretations and uses of test scores. Journal of Educational Measurement, 50(1), 1–73. https://doi.org/10.1111/jedm.12000
  • Lascano Pérez, M. J., & Altamirano Carvajal, S. P. (2025). Aplicación de la Inteligencia Artificial en las habilidades productivas y receptivas en la enseñanza del idioma inglés. DATEH,
  • 7(1).
  • Liu, X. J., Wang, J., & Zou, B. (2025). Evaluating an AI speaking assessment tool: Score accuracy, perceived validity, and oral peer feedback. Journal of English for Academic Purposes, 75, 101505.
  • López-Minotta, K. L., Chiappe, A., & Mella-Norambuena, J. (2025). Implementation of artificial intelligence to improve English oral expression. Multidisciplinary Journal of Educational Research (REMIE), 15(1), 43-71. https://doi.org/10.17583/remie.16188
  • Nigmatulina, I., Kew, T., & Samardžić, T. (2020). ASR for non-standardised languages with dialectal variation: The case of Swiss German. In M. Zampieri, P. Nakov, N. Ljubešić, J. Tiedemann, & Y. Scherrer (Eds.), Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects (pp. 15–24). International Committee on Computational Linguistics (ICCL). https://aclanthology.org/2020.vardial-1.2/
  • Raud, N. (2025). Automatic assessment of L2 interactional competency [Master’s thesis, Aalto University].
  • Saputra, A. E., & Widiastuty, H. (2024). The role of artificial intelligence in overcoming challenges in learning English speaking skills. International Seminar Universitas Tulungagung, 6, 162-171.
  • Valle Torres, M. (2025). Aporte de la Inteligencia Artificial o plataforma como medio de aprendizaje de inglés para el desarrollo de habilidades lingüísticas en estudiantes de Ingeniería. Ciencia Latina Revista Científica Multidisciplinar, 9(6). https://doi.org/10.37811/cl_rcm.v9i6.21465
  • Voss, E., Cushing, S. T., Ockey, G. J., & Yan, X. (2023). The use of assistive technologies including generative AI by test takers in language assessment: A debate of theory and practice. Language Assessment Quarterly, 20(4-5), 520-532. https://doi.org/10.1080/15434303.2023.2288256
  • Yi, P., Xia, Y., & Long, Y. (2025). Irony detection, reasoning and understanding in zero-shot learning. arXiv. https://doi.org/10.48550/arXiv.2501.16884
  • Zou, B., et al. (2024). Exploring EFL learners’ perceived promise and limitations of using an artificial intelligence speech evaluation system. System, 126, 103497.

 

Files

History

  • Receive Date: 02 February 2026
  • Revise Date: 16 February 2026
  • Accept Date: 16 February 2026

Share

How to cite

Statistics