DeepSeek vs. ChatGPT: Comparative Efficacy  in Reasoning for Adults’ Second Language  Acquisition Analysis

Mohammad Mahyoob Albuhairy; Jeehaan Algaraady

doi:10.55074/hesj.vi44.1313

المؤلفون

Mohammad Mahyoob Albuhairy Department of Languages and Translation Taibah University, Madina, KSA
Jeehaan Algaraady Department of Languages and Translation Taiz University, Yemen

DOI:

https://doi.org/10.55074/hesj.vi44.1313

الكلمات المفتاحية:

DeepSeek، ChatGPT، LLMs، Mother Tongue Influence (MTI)، Second Language Acquisition (SLA)، AI-Assisted Error Detection، Contrastive Linguistics

الملخص

The advent of new generation language models has revolutionized the field of natural language processing (NLP) due to their exceptional understanding and human language generation capabilities. ChatGPT emerged as an essential model with remarkable strengths for various applications. DeepSeek has recently emerged as the latest advancement in NLP, showing great potential in pure text-generation jobs, semantic analysis, and context-dependent language modeling capabilities. The study investigates and compares the performance of DeepSeek and ChatGPT in assessing adult L2 (second language) acquisition errors applied primarily to South Asian Arabic learners. With this premise, we aim to evaluate their efficacy in detecting linguistic inaccuracies (morphology, syntax, semantics) and diagnosing cases of L1 (first language). Methods include error analysis of non-native Arabic sentences, comparative evaluation of the two models, and contrasting assessment of depth of reasoning. Results show that DeepSeek was significantly better at context-driven error detection (for instance, in detecting SOV word-order transfer), and ChatGPT presented more instructively relevant feedback. However, both needed fine-tuned prompts to bring in feedback related to semantic/pragmatic errors, such as missing articles and dialectal mismatches. Contributions include a proposal for integrating AI tools into L2 pedagogy, emphasizing contrastive drill and sociolinguistic awareness, and recommendations for training AI concerning L1-targeted error profiles. This research pushes the integration of AI into language instruction for scalable solutions for adult L2 learners while pointing at improvements needed in the models.

التنزيلات

تنزيل البيانات ليس متاحًا بعد.

المراجع

Al-Garaady, J., & Mahyoob, M. (2023). ChatGPT's capabilities in spotting and analyzing writing errors experienced by EFL learners. Arab World English Journals, Special Issue on CALL, (9).

Chai, Y., Jin, L., Feng, S., & Xin, Z. (2024). Evolution and advancements in deep learning models for Natural Language Processing. Applied and Computational Engineering. https://doi.org/10.54254/2755-2721/77/20240674.

Chowdhury, M., & Haque, A. (2023). ChatGPT: Its Applications and Limitations. 2023 3rd International Conference on Intelligent Technologies (CONIT), 1-7.

https://doi.org/10.1109/CONIT59222.2023.10205621.

Chubaryan, A., & Vardanyan, M. (2024). EXPLORING THE COGNITIVE DIMENSIONS OF LANGUAGE ACQUISITION. Armenian Folia Anglistika. https://doi.org/10.46991/afa/2024.20.1.13.

Ellis, R. (2008). *The Study of Second Language Acquisition*. Oxford University Press.

Fraiwan, M., & Khasawneh, N. (2023). A Review of ChatGPT Applications in Education, Marketing, Software Engineering, and Healthcare: Benefits, Drawbacks, and Research Directions. ArXiv, abs/2305.00237. https://doi.org/10.48550/arXiv.2305.00237.

Hariri, W. (2023). Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing. ArXiv, abs/2304.02017. https://doi.org/10.48550/arXiv.2304.02017.

Krashen, S. D. (1982). *Principles and Practice in Second Language Acquisition*. Pergamon.

Krashen, S. (1985). The input hypothesis: Issues and implications. Longman.

Kumar, R., J, P., S, G., Devadas, R., Ambreen, L., & Pal, R. (2024). Emerging Trends of Language Models and Their Significance in Digital Era. 2024 Second International Conference on Advances in Information Technology (ICAIT), 1, 1-4. https://doi.org/10.1109/ICAIT61638.2024.10690389.

Le, N., Hadiprodjo, N., El-Alfy, H., Kerimzhanov, A., & Teshebaev, A. (2023). The Recent Large Language Models in NLP. 2023 22nd International Symposium on Communications and Information

Technologies (ISCIT), 1-6.

https://doi.org/10.1109/ISCIT57293.2023.10376050.

Lenneberg, E. H. (1967). Biological foundations of language. Wiley.

Lo, C. (2023). What Is the Impact of ChatGPT on Education? A Rapid Review of the Literature. Education Sciences.

https://doi.org/10.3390/educsci13040410.

Mahyoob, M., Al-Garaady, J., & Alblwi, A. (2023). A proposed framework for human-like language processing of ChatGPT in academic writing. International Journal of Emerging Technologies in Learning (iJET), 18(14).

Mahyoob, M. (2020). Challenges of e-Learning during the COVID-19 Pandemic Experienced by EFL Learners Arab World English Journal (AWEJ).

Mustafa, M., Masnan, A., Alias, A., & Radzi, N. (2018). Sociocultural Theories in Second Language Acquisition. The International Journal of Academic Research in Business and Social Sciences, 7, 1168-1171. https://doi.org/10.6007/IJARBSS/V7-I12/3747.

Masoudi, H. (2024). Effectiveness of ChatGPT in Improving English Writing Proficiency among Non-native English Speakers. International Journal of Educational Sciences and Arts.

https://doi.org/10.59992/ijesa.2023.v3n4p2.

Prasetya, R., & Syarif, A. (2023). ChatGPT as a Tool for Language Development: Investigating Its Impact on Proficiency and Self-Evaluation Accuracy in Indonesian Higher Education. VELES (Voices of English Language Education Society).

https://doi.org/10.29408/veles.v7i3.19303.

Showalter, C., & Hayes-Harb, R. (2015). Native English speakers learning Arabic: The influence of novel orthographic information on second language phonological acquisition. Applied Psycholinguistics, 36, 23 - 42. https://doi.org/10.1017/S0142716414000411.

Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.