Human Translation and AI: Reimagining EAP/EFL Pedagogy in the Language of Emotions. The Cases of "The Diary of Anaïs Nin" and "Gratitude" by Oliver Sacks

Abstract

This study investigates the role of AI-powered literary translation in English for Academic Purposes (EAP) and English as a Foreign Language (EFL) education by comparing human and AI translations of emotionally rich literary texts. It examines how AI affects translation quality, emotional expression, and learners' linguistic, cultural, and critical competencies.

Methods

The study involved 106 students who translated excerpts from literary diaries into Italian and compared their work with translations generated by ChatGPT, DeepL, and Google Translate. Translation quality was assessed using TF-IDF and cosine similarity analyses, emotional detection models, and a questionnaire exploring students' experiences with AI-assisted translation.

Results

Human translations demonstrated greater variability, creativity, and emotional sensitivity than AI-generated translations, particularly when translating metaphorical and emotionally complex passages. AI translations were generally more consistent and linguistically accurate but tended to standardize expression and reduce emotional intensity.

Conclusions

The findings indicate that AI is a valuable support tool for language learning and translation but cannot replace the creativity, contextual understanding, and emotional awareness of human translators. Integrating AI into EAP/EFL classrooms can enhance learning outcomes when combined with critical thinking and human expertise.

CONFLICT OF INTEREST

The authors declare no conflict of interest.

REFERENCES

• Bąk, H. (2023). Issues in the translation equivalence of basic emotion terms. Ampersand, 11,100128. https://doi.org/10.1016/j.amper.2023.100128
• Freitag, M., Foster, G., Grangier, D., Ratnakar, V., Tan, Q., & Macherey, W. (2021). Experts, errors, and context: A large-scale study of human evaluation for machine translation. Transactions of the Association for Computational Linguistics, 9, 1460–1474. https://doi.org/10.1162/tacl_a_00437
• Koskinen, K. (2020). Translation and affect: Essays on sticky affects and translational affective labour. John Benjamins.
• Liu, Y., Lee, S. Y. M., & Li, D. (2025). Examining emotions in English and translated Chinese children’s literature: A bilingual emotion detection model based on LLMs. Language Resources and Evaluation. https://doi.org/10.1007/s10579-025-09846-z
• Mastela, O. (2020). Retelling legends and folk tales: A transcreative approach in the collaborative translation classroom. Research in Language, 18(2), 151–171.
• Nin, A. (1975). The diary of Anaïs Nin: Volume 5, 1947–1955. Harvest/HBJ Book.
• Qian, S., Orasan, C., do Carmo, F., & Kanojia, D. (2023). Challenges of human vs machine translation of emotion-loaded Chinese microblog texts. In Proceedings of Machine Translation Summit XIX: Users Track (Vol. 2, pp. 217–236). Asia-Pacific Association for Machine Translation. https://aclanthology.org/2023.mtsummitusers.21.pdf
• Sacks, O. (2015). Gratitude. Alfred A. Knopf. Vanmassenhove, E., Shterionov, D., & Way, A. (2019). Lost in translation: Loss and decay of linguistic richness in machine translation. In Proceedings of Machine Translation Summit XVII: Research Track (pp. 222–232). European Association for Machine Translation. https://aclanthology.org/W19-6622/
• Venuti, L. (1995). The translator’s invisibility: A history of translation. Routledge.
• Yu, C. (2022). Online collaborative translation in China and beyond: Community, practice, and identity. Routledge.

Citing Literature