This paper presents results of comparing translations of classic French novels into English and Polish made by humans and by ChatGPT 4.1. the quantitative methods include comparisons of cluster analysis of most-frequent-word based distance measures, sentence length distribution by Dynamic Time Warping, vocabulary richness, Flesch-Kincaid Grade level, noun- and verb-phrase frequency, and translation-to-original word ratio. The results are compared with earlier studies by selected scholars.

Measuring semantic similarity across languages is central to many NLP, computational social science, and digital humanities workflows, yet most high-performing similarity models are monolingual and operate in language-specific embedding spaces. A common workaround is pivot translation: machine-translate all texts into a hub language (typically English) and then compute similarity using strong English encoders. This paper tests a key assumption behind that practice—whether corpus-level textual similarity is invariant under machine translation—using the Party Manifesto Corpus (2,878 documents in 28 eTranslation-supported languages). We segment manifestos into approximately single-topic pseudo-paragraphs via sentence splitting and change-point detection, align source and translated sentences with a monotone dynamic-programming procedure, and compute pseudo-paragraph embeddings using (i) language-specific models on originals, (ii) English models on translations, and (iii) multilingual models as a benchmark. Invariance is quantified by correlating paragraph–paragraph cosine similarity matrices (representational similarity analysis) and by nonparametric tests comparing translation-induced shifts to within-language model variability. We find that translation typically perturbs similarity structure: correlations between original-language and translation-based similarity matrices are often lower than correlations among original-language models, with substantial heterogeneity across languages. However, selecting the best-performing English encoder per language markedly reduces this gap, and multilingual models are generally more stable but not universally superior. Importantly, downstream impacts on ideological classification, clustering, and dimensionality reduction are smaller than representational distortions, suggesting that translation noise often preserves task-relevant structure. The results provide language-specific guidance on when translation-plus-English embeddings are sufficient and when multilingual representations are preferable.

The analysis of literary influence has a long history (e.g. Bloom, 1973) yet has received new attention occasioned by the arrival of new computational techniques. Stylometric analysis has been used successfully to analyse different kinds of collaboration in writing and translating. Whereas in collaboration contributions are more concrete and measurable, influence is more diffuse and more difficult to prove. In this paper, we investigate reviewer Carrie O’Grady claim that Christina Dalcher, whose work explicitly flaunts Atwoodesque themes, jumps ‘on the Handmaid’s Tale bandwagon’ (O’Grady 2018). An earlier, related study investigated the mutual influence between Margaret Atwood and Naomi Alderman, which could be the effect of their Rolex Mentor and Protégé collaboration (Coady 2013) during 2012–13. Based on our computational measurements of a selection of sf, speculative and/or dystopian novels written by women between 1976-2024, we indeed see that, rather than merging into a newly unique, blended or averaged style, Atwood’s and Alderman’s work reflects a sustained, reciprocal aesthetic exchange. Our analyses of Christina Dalcher’s novels VOX and Femlandia show that her work aligns itself with a broader field of speculative fiction rather than with either Atwood or Alderman. The analyses also show that she has a style that is different and distinct. To understand if genre is not a deciding factor in these results, two further experiments find Dalcher amongst the literary fiction, and not amongst the popular, Crime or Romance novels. Yet, she is not close to Atwood and Alderman. Although a superficial reading of Dalcher’s work might make it seem she is a copycat of Atwood (and Alderman), we do not find evidence of stylistic convergence, or even imitation. Dalcher has, though perhaps thematically inspired by Atwood (and Alderman), carved out a literary space of her own.