Lexicalizing Affective Meaning in Published and LLM-Generated Literary Translation: A Corpus-Based Study of Chinese Translations of Margaret Mitchell’s Gone with the Wind

Authors

  • Dandan Wu Beijing International Studies University, China
  • Yuxi Chang Beijing International Studies University, China

DOI:

https://doi.org/10.61360/BoniGHSS262020520408

Keywords:

literary translation, affective meaning, LLM translation, lexical explicitness, prompting

Abstract

This study examines how affective and evaluative meaning is lexicalized in published Chinese translations and large language model (LLM) outputs of literary prose. The corpus comprises 98 purposively selected English sentences from Margaret Mitchell’s Gone with the Wind, three published Chinese translations, and twelve LLM outputs generated by six systems under a general translation prompt and an emotion-and-style-oriented prompt. Affective explicitness is operationalized through the density and type range of contextually validated entries in the DUTIR Chinese Emotion Ontology; lexical convergence through word- and category-level Jaccard overlap among versions aligned to the same source sentence. The comparisons use 36 complete-case sentence groups in which all 15 versions contain at least one retained DUTIR item. In this sensitivity sample, LLM outputs show higher dictionary-recognized affective-word density and broader type ranges than the published translations, alongside greater within-condition lexical convergence. The second prompt leaves aggregate density largely unchanged, increases distinct-type counts, and reduces cross-model word overlap. The findings treat lexical visibility and convergence as properties of output form rather than proxies for affective intensity, literary quality, or translation superiority.

References

Baker, M. (1993). Corpus linguistics and translation studies: Implications and applications. In M. Baker, G. Francis, & E. Tognini-Bonelli (Eds.), Text and technology: In honour of John Sinclair (pp. 233–250). John Benjamins. https://doi.org/10.1075/z.64.15bak

Bednarek, M. (2008). Emotion talk across corpora. Palgrave Macmillan. https://doi.org/10.1057/9780230285712

Calvo-Ferrer, J. R. (2024). Can you tell the difference? A study of human vs machine-translated subtitles. Perspectives, 32(6), 1115–1132. https://doi.org/10.1080/0907676X.2023.2268149

Chen, L., Varga, L., & Mehdizadkhani, M. (2026). Taming AI for The Little Prince: A comparative analysis of NMTs and LLMs in Hungarian translation. Humanities and Social Sciences Communications, 13, 46. https://doi.org/10.1057/s41599-025-06343-0

Gao, R., Lin, Y., Zhao, N., et al. (2024). Machine translation of Chinese classical poetry: A comparison among ChatGPT, Google Translate, and DeepL Translator. Humanities and Social Sciences Communications, 11, 835. https://doi.org/10.1057/s41599-024-03363-0

Hood, S. (2010). Appraising research: Evaluation in academic writing. Palgrave Macmillan. https://doi.org/10.1057/9780230274662

House, J. (2015). Translation quality assessment: Past and present. Routledge. https://doi.org/10.4324/9781315752839

Hu, K., & Li, X. (2023). The creativity and limitations of AI neural machine translation: A corpus-based study of DeepL’s English-to-Chinese translation of Shakespeare’s plays. Babel, 69(4), 546–563. https://doi.org/10.1075/babel.00331.hu

Liu, Y. (2026). Unmasking sentiment disguise in cross-cultural literary translation: Analyzing Oscar Wilde’s The Happy Prince and its heartbroken audience. Humanities and Social Sciences Communications, 13, 193. https://doi.org/10.1057/s41599-026-06491-x

Martin, J. R., & White, P. R. R. (2005). The language of evaluation: Appraisal in English. Palgrave Macmillan.

Mitchell, M. (1947). Gone with the Wind. The Macmillan Company.

Mitchell, M. (2001). 飘 [Gone with the Wind] (L. Meihua, Trans.). Yilin Press.

Mitchell, M. (2004). 飘 [Gone with the Wind] (D. Kexin, L. Yuzhong, & Y. Zhuang, Trans.). People’s Literature Publishing House.

Mitchell, M. (2008). 飘 [Gone with the Wind] (F. Donghua, Trans.). Zhejiang Literature and Art Publishing House.

O’Brien, S. (2024). Human-centred augmented translation: Against antagonistic dualisms. Perspectives, 32(3), 391–406. https://doi.org/10.1080/0907676X.2023.2247423

Terando, L. (2023). Recasting the unspeakable: Pain, suffering and loss. The Translator, 29(1), 17–27. https://doi.org/10.1080/13556509.2021.2022853

Xu, L., Lin, H., Pan, Y., Ren, H., & Chen, J. (2008). 情感词汇本体的构造 [Construction of an emotion lexicon ontology]. Journal of the China Society for Scientific and Technical Information, 27(2), 180–185.

Downloads

Published

2026-08-19

Issue

Section

Generative AI in the Humanities: Methods, Applications, and Critical Perspectives

How to Cite

Lexicalizing Affective Meaning in Published and LLM-Generated Literary Translation: A Corpus-Based Study of Chinese Translations of Margaret Mitchell’s Gone with the Wind. (2026). Journal of Global Humanities and Social Sciences, 1(1), 1-9. https://doi.org/10.61360/BoniGHSS262020520408

Similar Articles

11-20 of 24

You may also start an advanced similarity search for this article.