ANALISIS KUALITAS TERJEMAHAN DEEPSEEK DAN GEMINI AI PADA TEKS POLITIK MENGGUNAKAN FRAMEWORK KARANGTURI: Analisis Kualitas Terjemahan Deepseek dan Gemini pada Artikel Politik Berbahasa Prancis Menggunakan Kerangka Kerja Karangturi

Zalfaa Azhaar Maziyah; Farida Amalia; Ariessa Racmadhany

doi:10.58194/eloquence.v5i2.3753

Authors

Zalfaa Azhaar Maziyah Universitas Pendidikan Indonesia
Farida Amalia Universitas Pendidikan Indonesia
Ariessa Racmadhany Universitas Pendidikan Indonesia

DOI:

https://doi.org/10.58194/eloquence.v5i2.3753

Keywords:

Artificial Intelligence (AI), DeepSeek, Gemini, Translation Quality, French Political Texts

Abstract

Background: The rapid integration of AI in machine translation has spurred extensive research, with over 2,000 studies (2024–2026) on translation quality, mostly focused on general and literary texts. This leaves a gap in evaluating complex political texts, where cultural nuances and specialized terminology pose unique challenges.

Purpose: This research is carried out with the objective to examine level of accuracy, acceptability, and readability of the translated results of French political news texts translated by DeepSeek and Gemini using Karangturi framework belongs to Honggo to find a model of AI that shows excellent translation quality based on Nababan's accuracy and readability theory and Machali's acceptability theory.

Method: The research method used is descriptive qualitative with research data taken from three news portals in France, namely Le Figaro, Libération, and Le Monde, each of which represents different political ideologies. The research instrument uses Nababan's accuracy and readability theory and Machali's acceptability theory, modified by Ardi.

Results and Discussion: The test results show the same accuracy score (87.04%) and

acceptability (82.64%) by both AI machines. However, Gemini is more excellent in readability with a score of 98.61% compared to DeepSeek, which scored 93.06%. Therefore, in total, Gemini (89.65%) better than DeepSeek (87.63%).

Conclusions and Implications: This study concludes that Gemini and DeepSeek have great potential in translating political news texts, but their translation results still require human editing due to limitations in grammatical and contextual aspects. These results can be used as an academic reference for researchers and students to be more critical of the role of AI in the transfer of socio-political meaning, and also suggest that future researchers explore other AI frameworks or machines to expand the scope of this research.

References

[1] R. Shahmerdanova, “Artificial Intelligence in Translation: Challenges and Opportunities,” Acta Globalis Humanitatis et Linguarum, vol. 2, no. 1, pp. 62–70, Jan. 2025, doi: https://doi.org/10.69760/aghel.02500108.

[2] M. Huang, “Application of Artificial Intelligence in Machine-Assisted Translation Systems,” 2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques (EASCT), Oct. 2023, doi: https://doi.org/10.1109/easct59475.2023.10392488.

[3] A. Genovese et al., “Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation,” Annals of Translational Medicine, vol. 12, no. 6, pp. 117–117, Dec. 2024, doi: https://doi.org/10.21037/atm-24-162.

[4] F. F. Siyam, R. Hidayat, C. S. Rochmat, R. D. Maulaya, A. Avilya, and M. B. Maulidi, “Accuracy Analysis of Artificial Intelligence in Arabic Language Translation and Grammatical Rule Mapping,” Jurnal Al Bayan Jurnal Jurusan Pendidikan Bahasa Arab, vol. 16, no. 2, pp. 558–558, Dec. 2024, doi: https://doi.org/10.24042/albayan.v16i2.24588.

[5] A. GURUNG, “Role Of Media In Shaping Public Opinion,” Zenodo, vol. 05, no. 05, May 2025, doi: https://doi.org/10.5281/zenodo.15363508.

[6] H. A. Sukmono and A. Basid, “Critical Discourse Analysis of Media Power in Reporting the 19% US Tariff on Indonesian Exports: A Comparative Study of Indonesian and Middle East News Outlets,” ELOQUENCE : Journal of Foreign Language, vol. 4, no. 3, pp. 440–458, 2025, doi: https://doi.org/10.58194/eloquence.v4i3.3028.

[7] N. Cherikbaeva and T. Musaeva, “Political Discourse And Its Role In Shaping Public Opinion,” Alatoo Academic Studies, vol. 24, no. 1, pp. 277–290, Mar. 2024, doi: https://doi.org/10.17015/aas.2024.241.25.

[8] S. Vraila, “AI in Political Translation: Revolutionising Communication or Risking Manipulation?,” New Trends in Translation and Technology Conference 2024, pp. 226–229, Jan. 2024, doi: https://doi.org/10.26615/issn.2815-4711.2024_019.

[9] S. K. K. Aldulaimi, “Translation Challenges of Political Terms between Arabic and English: A Comparative Analytical Study in Diplomatic Discourse,” The International and Political Journal, vol. 64, no. 64, pp. 523–530, Sep. 2025, doi: https://doi.org/10.31272/ipj.i64.502.

[10] A.-E. Oneţ and A.-B. Ciocoi-Pop, “The Role of the Translator in Nowadays’ Politically Charged International Environment,” International conference KNOWLEDGE-BASED ORGANIZATION, vol. 29, no. 2, pp. 221–226, Jun. 2023, doi: https://doi.org/10.2478/kbo-2023-0061.

[11] M. Al-Amin et al., “History of generative Artificial Intelligence (AI) chatbots: past, present, and future development,” arXiv.org, Feb. 04, 2024. https://arxiv.org/abs/2402.05122

[12] H. Twinomurinzi and S. Gumbo, “ChatGPT in Scholarly Discourse: Sentiments and an Inflection Point,” Communications in computer and information science, vol. 1878, pp. 258–272, Jan. 2023, doi: https://doi.org/10.1007/978-3-031-39652-6_17.

[13] D. Hassabis, “Memperkenalkan Gemini: Model AI Kami Yang Terbesar Dan Tercanggih,” Google, Dec. 12, 2023. https://blog.google/intl/id-id/company-news/technology/2023_12_memperkenalkan-gemini-model-ai-kami-yang-terbesar-dan-paling-mumpuni/ (accessed Jun. 15, 2026).

[14] R. Li, “DeepSeek: Revolutionising the AI Industry,” Feb. 2025, doi: https://doi.org/10.62436/a-1740063218021.

[15] R. I. Pratiwi and M. Gusthini, “ChatGPT sebagai Alat Penerjemahan AI untuk Puisi ‘Hope is the Thing with Feathers,’” Jurnal Ilmu Sosial dan Humaniora., vol. 3, no. 4, pp. 513–526, Jun. 2025, doi: https://doi.org/10.57248/jishum.v3i4.589.

[16] N. T. Hidayatullah and Aliurridha, “Evaluasi Komparatif Kualitas Terjemahan Ai: Gemini Vs Chatgpt Pada Novel The Lord Of The Rings (The Two Towers),” Jurnal Lisdaya, vol. 21, no. 1, pp. 75–82, 2025, Accessed: Jun. 15, 2026. [Online]. Available: https://lisdaya.unram.ac.id/index.php/lisdaya/article/view/123

[17] F. Humolungo, F. P. Rakhmi, and T. G. Napitupulu, “Analisis Komparatif Performa Chatgpt dan Deepl dalam Menerjemahkan Teks Jurnalistik Indonesia-Inggris,” Seminar Nasional Riset Terapan, vol. 14, no. 01, pp. 160–169, 2025, Accessed: Jun. 15, 2026. [Online]. Available: https://prosiding.pnj.ac.id/index.php/snrtb/article/view/5857

[18] M. Hasyim, Buku Ajar Mata Kuliah Teori Terjemahan. Universitas Hasanuddin, 2015.

[19] J. C. Catford, A Linguistic Theory of Translation an Essay in Applied Linguistics, 5th ed. Oxford University Press, 1978.

[20] E. A. Nida and C. R. Taber, The Theory and Practice of Translation. Leiden: E.J. Brill, 1969.

[21] M. L. Larson, Meaning-based Translation. University Press of America, Inc., 1998.

[22] B. Hatim and I. Mason, The Translator as Communicator. London ; New York: Routledge, 1997.

[23] P. Newmark, A textbook of translation. Harlow: Longman, 1988.

[24] R. Machali, Pedoman bagi Penerjemah. PT Mizan Publika, 2009.

[25] E. Sulaiman, “Penerapan Metode Terjemah Dalam Pembelajaran Bahasa Arab Di Madrah Aliyah Sukorejo Situbondo,” Ulumuna: Jurnal Studi Keislaman, vol. 3, no. 1, pp. 98–117, 2017, Accessed: Jun. 15, 2026. [Online]. Available: https://ejournal.kopertais4.or.id/madura/index.php/ulumuna/article/view/4119

[26] M. Furlan, “Étienne Dolet e o ‘modo de traduzir bem de uma língua a outra,’” Cadernos de Tradução, vol. 1, no. 21, Nov. 2008, doi: https://doi.org/10.5007/2175-7968.2008v1n21p67.

[27] K. Lloyd-Jones, “Valeur classique ou valeur humaniste: qu’est-ce que la rhétorique pour Dolet?,” International Journal of the Classical Tradition, vol. 6, no. 1, pp. 21–29, Sep. 1999, doi: https://doi.org/10.1007/bf02689208.

[28] H. Ardi, Pengantar Penerjemahan. Penerbit Sukabina Press, 2015.

[29] R. Siregar, “Pentingnya Pengetahuan Ideologi Penerjemahan Bagi Penerjemah,” Jurnal Penelitian Pendidikan Bahasa Dan Sastra, vol. 1, no. 1, pp. 20–27, 2016, Accessed: Jun. 15, 2026. [Online]. Available: https://jurnal-lp2m.umnaw.ac.id/index.php/JP2BS/article/view/19

[30] F. Amalia, “Ideologi Dalam Penerjemahan,” Academia.edu, Dec. 09, 2016. https://www.academia.edu/30352187/IDEOLOGI_DALAM_PENERJEMAHAN (accessed Jun. 15, 2026).

[31] M. Nababan, A. Nuraeni, and Sumardiono, “Pengembangan Model Penilaian Kualitas Terjemahan ,” Kajian Lingustik dan Sastra, vol. 24, no. 1, pp. 39–57, 2012, doi: https://doi.org/10.23917/kls.

[32] A. Kudra, “News jako funkcja,” Acta Universitatis Lodziensis. Folia Litteraria Polonica, vol. 13, pp. 399–404, Jan. 2010, doi: https://doi.org/10.18778/1505-9057.13.28.

[33] N. A. Akhrenova and R. I. Zaripov, “Structural Features of News Text in Internet Discourse,” Moscow University Bulletin. Series 19. Linguistics and Intercultural Communication, vol. 26, no. №3_2023, pp. 87–98, Nov. 2023, doi: https://doi.org/10.55959/msu-2074-1588-19-26-3-6.

[34] M. A. Dzhasim, “Problemy Perevoda obshchestvenno-politologicheskikh Terminov,” Current Trends in the Development of Education System, pp. 263–265, Sep. 2023, doi: https://doi.org/10.31483/r-107714.

[35] S. Aslonov and M. Saidova, “Peculiarities Of Translation Of Political Texts In Simultaneous Interpretation,” Ижтимоий-гуманитар Фанларнинг Долзарб Муаммолари / Актуальные Проблемы социально-гуманитарных Наук / Actual Problems of Humanities and Social Sciences., vol. 4, no. 4, Apr. 2024, doi: https://doi.org/10.47390/spr1342v4i4y2024n34.

[36] K. Sárosi-Márdirosz, “Problems Related to the Translation of Political Texts,” Acta Universitatis Sapientiae, Philologica, vol. 6, no. 2, pp. 159–180, Mar. 2015, doi: https://doi.org/10.1515/ausp-2015-0012.

[37] H. A. Rahman, A. L. Pramudya, K. Syalsabila, I. I. Mulya, and I. Triadi, “Studi Komparatif Sistem Presidensial Dalam Pemerintahan Negara Indonesia Dan Prancis,” Causa, vol. 16, no. 2, pp. 121–130, 2025, doi: https://doi.org/doi.org/10.3783/causa.v2i9.2461.

[38] A. Knapp, “France’s Party System in 2022,” Modern & Contemporary France, vol. 30, no. 4, pp. 1–21, Nov. 2022, doi: https://doi.org/10.1080/09639489.2022.2134849.

[39] T. R. Martin and L. Binet, “Left versus Right, or Mainstream versus Margins? Divisions in French Media and Reactions to the ‘Brexit’ Vote,” pp. 145–167, Jan. 2018, doi: https://doi.org/10.1007/978-3-319-73682-2_9.

[40] A. Fadhil, M. Hasyim, and Wahyuddin, “Struktur Teks Media Daring Prancis Dalam Pemberitaan Mengenai Niis (Suatu Analisis Wacana Kritis),” Jurnal Ilmu Budaya, vol. 3, no. 1, pp. 500–525, Jun. 2015.

[41] J. Kumar, S. K. Henge, and P. Dubey, “An Intensive Literature Review on Machine Translation Using Neural Approach,” in Lecture Notes in Electrical Engineering, Springer Science Business Media, Jan. 2022, pp. 45–59. doi: https://doi.org/10.1007/978-981-16-8248-3_4.

[42] S. A. Mohamed, A. A. Elsayed, Y. F. Hassan, and M. A. Abdou, “Neural Machine translation: past, present, and Future,” Neural Computing and Applications, vol. 33, Jul. 2021, doi: https://doi.org/10.1007/s00521-021-06268-0.

[43] R. Jagtap and S. N. Dhage, “An In-depth Walkthrough on Evolution of Neural Machine Translation,” arXiv: Computation and Language, Apr. 10, 2020. https://doi.org/10.48550/arXiv.2004.04902 (accessed Jun. 16, 2026).

[44] MD. A. A. Ansary, “Neural Machine Translation between English and Bangla: a Philosophical Survey Observing Architectures and Performances,” IOSR Journal of Computer Engineering, vol. 26, no. 5, pp. 17–25, Oct. 2024, doi: https://doi.org/10.9790/0661-2605011725.

[45] F. C. P. Arredondo, J. I. C. Taipe, and M. A. Cruz, “Revisión Sistemática De La Evolución De Los Asistentes virtuales: Desde Los Primeros Chatbots Hasta La IA Conversacional,” Micaela Revista De Investigación - UNAMBA, vol. 5, no. 2, pp. 33–39, Oct. 2024, doi: https://doi.org/10.57166/micaela.v5.n2.2024.154.

[46] K. Wang, “From ELIZA to ChatGPT: a Brief History of Chatbots and Their Evolution,” Applied and Computational Engineering, vol. 39, no. 1, pp. 57–62, Feb. 2024, doi: https://doi.org/10.54254/2755-2721/39/20230579.

[47] P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, “Pre-train, Prompt, and Predict: a Systematic Survey of Prompting Methods in Natural Language Processing,” ACM Computing Surveys, vol. 55, no. 9, Sep. 2022, doi: https://doi.org/10.1145/3560815.

[48] J. White et al., “A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT,” arXiv, Feb. 2023, doi: https://doi.org/10.48550/arxiv.2302.11382.

[49] L. Reynolds and K. McDonell, “Prompt Programming for Large Language Models: beyond the Few-Shot Paradigm,” Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, May 2021, doi: https://doi.org/10.1145/3411763.3451760.

[50] S. Mishra, D. Khashabi, C. Baral, and H. Hajishirzi, “Cross-Task Generalization via Natural Language Crowdsourcing Instructions,” arXiv.org, Mar. 14, 2022. https://arxiv.org/abs/2104.08773

[51] J.D. Zamfirescu-Pereira, R. Y. Wong, B. Hartmann, and Q. Yang, “Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts,” Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Apr. 2023, doi: https://doi.org/10.1145/3544548.3581388.

[52] T. B. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems 33, 2020.

[53] D. Zhou et al., “Least-to-Most Prompting Enables Complex Reasoning in Large Language Models,” in ICLR 2023, May 2022. doi: https://doi.org/10.48550/arxiv.2205.10625.

[54] J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” Advances in Neural Information Processing Systems, vol. 35, pp. 24824–24837, Dec. 2022, Available: https://proceedings.neurips.cc/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html

[55] S. Yao et al., “ReAct: Synergizing Reasoning and Acting in Language Models,” arXiv.org, Mar. 09, 2023. https://arxiv.org/abs/2210.03629

[56] H. Honggo, “Framework Karangturi Untuk Prompt Engineering: Analisis Komparatif Dengan Rtf, Cot, Dan React Pada Model Ai Generatif,” Science Technology and Management Journal, vol. 5, no. 2, pp. 133–138, Aug. 2025, doi: https://doi.org/10.53416/stmj.v5i2.353.