What question did this study set out to answer?

The aim is to compare the linguistic variability of AI-generated text with that of human-written text using quantitative metrics.

June 7, 2026Open Access

A Comparative Analysis of Variability in AI-Generated and Human-Written Text

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis investigates linguistic variability in AI-generated vs human-written text, suggesting implications for AI output.

The aim is to compare the linguistic variability of AI-generated text with that of human-written text using quantitative metrics.
Analyzed 172 human responses and 150 AI-generated responses to an open-ended prompt.
Measured linguistic variability using word count, sentence structure, and lexical diversity.
Used quantitative linguistic metrics for comparison of outputs.
AI-generated responses show significantly lower variance in linguistic features.
AI text exhibited greater structural consistency compared to human-written text.
Statistical regularisation is identified as a key characteristic of large language models.

Sahay et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark