Summary
This work looks at how AI can be guided to write novels by giving it a specific historical style, like Victorian, as a starting point. Instead of grouping books by time period after they are written, the AI starts with the time period in mind and writes accordingly. The researchers tested this idea by having AI tools write 100 novels using Victorian and neutral prompts, then measured how well the writing matched nineteenth-century styles. They found that some AI models followed the Victorian style better than others, showing that the style prompt influences the writing in measurable ways. However, the changes were broader to the nineteenth century style rather than strictly Victorian.
Generative AILiterary periodizationVictorian literatureGPTQwenLlamaGrammatical featuresPeriod Alignment ScoreNineteenth centuryAI-generated novels
Abstract
Generative AI inverts the typical periodization of literary history: the periodizing tag Victorian can now come first and influence what is written. Generative periodization, defined and tested here, describes the use of literary-period designations in generating texts. I test this approach on 100 book-length novels produced under Victorian and Zero-Style conditions using GPT, Qwen, and Llama workflows. The Period Alignment Score (PAS), trained on nineteenth-century literature and benchmarked against human Zero-Style prose, assesses alignment using topic-reduced grammatical features. Victorian prompts produce consistent historical-direction shifts in GPT and Qwen, but not robustly in Llama. Victorian-only recalibration and harder comparison corpora preserve the GPT and Qwen effects. Cross-model transfer also shows a shared direction of grammatical change. The measurable target is the broader nineteenth century rather than the Victorian period per se.