Pemanfaatan Deepsek Sebagai Perangkat Koreksi dalam Pembelajaran Murasalat (Korespondensi Arab) pada Mahasiswa Pendidikan Bahasa Arab Universitas Negeri Semarang
DOI:
https://doi.org/10.37680/aphorisme.v7i1.9277Keywords:
Artificial Intelligence, Deepseek, Murasalat, WritingAbstract
This study aims to evaluate the effectiveness of the DeepSeek artificial intelligence platform as a correction tool in the Murasalat course (Arabic correspondence) in the Arabic Language Education Study Program at Semarang State University. The background of this research is the complexity of Arabic proficiency for non-native Arabic speakers, encompassing grammar, vocabulary, and cultural sensitivity. The method used is a mixed-methods approach involving 30 fourth-semester students divided into experimental and control groups. The primary data consisted of students’ Arabic correspondence texts collected through pre-tests, post-tests, as well as questionnaire responses and semi-structured interviews. Quantitative data were analyzed using paired sample t-tests to determine differences between pre- and post-intervention scores, and effect size was calculated using Cohen’s d. Additionally, DeepSeek’s correction accuracy was measured across morphological, syntactic, semantic, and pragmatic error categories. Qualitative data were analyzed using thematic analysis to examine students’ perceptions of the tool. The results indicate that DeepSeek has high accuracy in detecting errors at the morphological, syntactic, semantic, and pragmatic levels, surpassing manual correction capabilities in several aspects. Statistical analysis revealed a significant improvement in scores among the experimental group, with a mean gain of 7,73 points and a very strong effect size (Cohen's d = 3.71). Students showed positive perceptions of this tool, as it provided instant feedback that enhanced their self-confidence. However, limitations were identified in detecting complex cultural-pragmatic nuances. This study concludes that integrating DeepSeek into the Arabic language curriculum can support more effective and accurate independent learning.
References
Aaron, S., & Mahamod, Z. (2025). Artificial Intelligence (AI) Technology in Learning Malay Language Literacy Skills among Students. International Journal of Research and Innovation in Social Science, 5982. https://doi.org/10.47772/ijriss.2025.909000486
Abdel-Malek, M. (2020). Empowering Arabic Learners to Make Meaning: A Genre-Based Approach. System, 94, 102329. https://doi.org/10.1016/j.system.2020.102329
Ajleaa, N., Rahman, A., Zulkornain, L. H., & Hamzah, N. H. (2022). Exploring Artificial Intelligence using Automated Writing Evaluation for Writing Skills. 547–553.
Al-Khatib, M. A. (2021). (Im)politeness in Intercultural Email Communication between People of Different Cultural Backgrounds: A Case Study of Jordan and the USA. Journal of Intercultural Communication Research, 50(4), 409–430. https://doi.org/10.1080/17475759.2021.1913213
Al-Mutawa, A. S. (2025). An Analysis of Business E-Mails Written by Arab Female Business Students. Journal of Language Teaching and Research, 16(3), 734–744. https://doi.org/10.17507/jltr.1603.04
Al-obaydi, L. H. (2025). DeepSeek as an AI-Powered Learning Tool : Uncovering EFL College Students ’ Preference and Satisfaction. December, 1–16. https://doi.org/10.1177/21582440251381683
Al-Sayyed, S., & Rabab’ah, G. (2020). Greeting and Farewell Formulas in English and Arabic Emails: A Contrastive Study. 14(5), 267–291. http://https//www.ijicc.net/index.php/volume-14-2020/202-vol-14-iss-5
Alafnan, M. A. (2025). DeepSeek vs ChatGPT : A Comparative Evaluation of AI Tools in Composition , Business Writing , and Communication Tasks. 202–210.
Alaiyed, M. A. (2024). Politeness Strategies in Email Opening and Closing Moves by Saudi Female EFL Students. Theory and Practice in Language Studies, 14(9), 2834–2842. https://doi.org/10.17507/tpls.1409.19
Albuhairy, M. M., & Algaraady, J. (2025). DeepSeek vs . ChatGPT : Comparative Efficacy in Reasoning for Adults ’ Second Language Department of Languages and Translation Department of Languages and Translation DeepSeek vs . ChatGPT : Comparative Efficacy. 44, 864–883.
Azwir, A. (2023). Lexical Problems in Indonesian-Arabic Translation at the Undergraduate Arabic Department. El-Maqalah : Journal of Arabic Language Teaching and Linguistics, 4(2), 144–155. https://doi.org/10.22373/maqalah.v4i2.3975
Bansal, S., Gupta, V., Gupta, E., & Garg, P. (2025). Evaluating Handwritten Answers using DeepSeek : A Comparative Analysis of Deep Learning ‑ Based Assessment.
Belbouah, A., Khotbi, T., & Bouguerba, T. (2023). Challenges of Writing in Arabic as a Foreign Language Context: Case of the Spanish School in Rabat. European Journal of Contemporary Education and E-Learning, 1(1), 3–19. https://doi.org/10.59324/ejceel.2023.1(1).01
Bodaubekov, A. (2025). Leveraging AI to Enhance Writing Skills of Senior TFL Students in Kazakhstan : A Case Study using “ Write & Improve .” 17(1), 1–17.
Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The Promises and Challenges of Artificial Intelligence for Teachers: a Systematic Review of Research. TechTrends, 66(4), 616–630. https://doi.org/10.1007/s11528-022-00715-y
Cerveró-carrascosa, A., & Sarno-garcía, S. Di. (2025). DeepSeek ’ s Feedback on Short Essay- Writing in EFL : Pre-service Primary School T eachers ’ Perceptions. 32(2), 38–48.
Chen, C., & Gong, Y. F. (2025). The Role of AI ‑ Assisted Learning in Academic Writing : A Mixed ‑ Methods Study on Chinese as a Second Language Students. 1–19.
Dajani, B. A. S., Mubaideen, S., & Omari, F. M. A. (2014). Difficulties of Learning Arabic for Non-native Speakers. Procedia - Social and Behavioral Sciences, 114(February 2014), 919–926. https://doi.org/10.1016/j.sbspro.2013.12.808
Ed-dali, R. (2025). Assessing DeepSeek R1 and ChatGPT 4 . 5 in Arabic-English Literary Translation : Performance , Challenges , and Implications. Cogent Arts & Humanities, 12(1). https://doi.org/10.1080/23311983.2025.2531183
Gao, H., Hashim, H., & Yunus, M. (2025). Assessing the Reliability and Relevance of DeepSeek in EFL Writing Evaluation : A Generalizability Theory Approach.
Hattie, J., & Timperley, H. (2007). The Power of Feedback. 77(1), 81–112. https://doi.org/10.3102/003465430298487
Hosni, H. R. (2020). Advice Giving in Egyptian Arabic and American English : A. Journal of Pragmatics, 155, 193–212. https://doi.org/10.1016/j.pragma.2019.11.001
Hu, S., & Wang, L. (2025). Effects of DeepSeek-assisted Writing Instruction on EFL Learners ’ Writing Performance. 692–697. https://doi.org/10.1145/3746469.3746577
Huda, M. M., Mahfudhoh, R., Tsanawiyah, M., & Keras, N. (2024). Enhancing Arabic Writing Skills Through the Genre-Based Approach in Senior High School. 4(2), 121–134.
Hwang, H., Chang, X., & Sun, J. (2025). Generative AI is useful for Second Language Writing, but When, Why, and for How Long Do Learners use it? Journal of Second Language Writing, 69(July), 101230. https://doi.org/10.1016/j.jslw.2025.101230
Law, L. (2024). Application of Generative Artificial Intelligence (Gen AI) in Language Teaching and Learning: A Scoping Literature Review. Computers and Education Open, 6(December 2023), 100174. https://doi.org/10.1016/j.caeo.2024.100174
Li, Z., Huang, Y., & Wang, M. (2025). Foreign Language Education Reform and Language Services Talents Training in the Era of Large Language Models. 9(3), 568–572. https://doi.org/10.26855/jhass.2025.03.023
Mahapatra, S. (2024). Impact of ChatGPT on ESL Students ’ Academic Writing Skills : A Mixed Methods Intervention Study. Smart Learning Environments. https://doi.org/10.1186/s40561-024-00295-9
Mitrovic, A. (2020). Learn teach &. https://doi.org/10.21554/hrr.042009
Mohideen, H. L. M. (n.d.). Exploring the Opportunities of Implementing Artificial Intelligence ( AI ) Technology for Teaching Arabic to Non-Native Speakers : A Theoretical Approach. 2(9).
Nabilla, M. . (2025). No Title. 12(4), 579–593.
Pratama, A., & Sulistiyo, U. (2024). A Systematic Review of Artificial Intelligence in Enhancing English Foreign Learners ’ Writing Skills. 3(October), 170–181.
Premier, I., & Of, J. (2025). From Prompt to Polite : The Efficacy of Generative AI in Fostering Digital Pragmatic Competence for English. 3(2), 1–25.
Putu, N., & Anggreni, Y. (2025). Analyzing Grammatical Errors in EFL Students ’ Opinion Essays using Deepseek AI : Patterns and Pedagogical Implications. 13, 211–218. https://doi.org/10.59672/stilistika.v13i2.4560
Rizqa, A., Siregar, F., Ichsanda, B., & Hz, R. (2025). Undergraduate Students ’ Perceptions on Utilizing Deepseek AI as a Tool in Writing Journal Articles. 12(2), 713–729.
Sinnappan, M., & Samat, N. A. (2024). Interlingual Error Analysis in the Writing of Tamil-Speaking College Students. 06(06), 965–977.
Uçar, M. M., & Koçak, M. (2026). Evaluating the Error Analysis Performance of the Deepseek AI Chatbot in Foreign Language Teaching. 53–65. https://doi.org/10.29329/almamater.2026.1417.4
Youn, C. H., Salam, A. R., & Rahman, A. A. (2025). AI-Driven Tools in Providing Feedback on Students ’ Writing. IX(2454), 58–67. https://doi.org/10.47772/IJRISS
Zhai, C., & Wibowo, S. (2023). A Systematic Review on Artificial Intelligence Dialogue Systems for Enhancing English as Foreign Language Students’ Interactional Competence in the University. Computers and Education: Artificial Intelligence, 4(September 2022), 100134. https://doi.org/10.1016/j.caeai.2023.100134
Zhang, Y., Wang, Y., & Zhou, Y. (n.d.). Practice of College English Writing Teaching Based on Large Language Models of DeepSeek. 1–6.
Zubaidi, A., Munip, A., Widodo, S. A., & Zerrouki, T. (2025). Enhancing Arabic Writing Skills using Chat GPT-Based AI Learning Models: A Tridimensional Human-AI Collaboration Framework. Indonesian Journal of Applied Linguistics, 15(1), 87–101. https://doi.org/10.17509/ijal.v15i1.75378
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Akbar Syamsul Arifin, Nafis Azmi Amrullah, Singgih Kuswardono, Ahmad Miftahuddin, Nailur Rahmawati, Hasan Busri
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
.jpg)
