Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Glottometrics

Comparative Statistical Analysis of Word Frequencies in Human-Written and AI-Generated Texts

View Full Paper
Ask AI
Bookmark
Share

Authors

AKAnna KudryavtsevaAKArtyom Kovalevskii

Discussion

Loading...

Member takes

Overview

Comparative study of word frequencies distinguishes AI-generated texts from human-written essays, highlighting vocabulary differences.

Key Points

  • The study finds that AI-generated texts exhibit a significantly smaller vocabulary compared to human-written texts.
  • Zipf diagrams reveal the vocabulary differences, but rare words do not effectively classify the texts.
  • Using the relative frequencies of key words and hapax legomena significantly improves text classification.
  • This approach uses six specific textual features to confidently identify the origins of the essays.

Cite This Study

Kudryavtseva et al. (2025) studied this question.

synapsesocial.com/papers/68c1b81254b1d3bfb60ebd4bhttps://doi.org/10.53482/2025_58_423
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Differentiating Between Human-Written and AI-Generated Texts Using Automatically Extracted Linguistic Features2025
  2. 2Differentiating Between Human-Written and AI-Generated Texts Using Automatically Extracted Linguistic Features2025
  3. 3A Comparative Analysis of Variability in AI-Generated and Human-Written Text2026
  4. 4Quantitative Analysis of Generative AI Text Usage and Identification of Factors Influencing Text Choice2026
  5. 5Differentiating between human-written and AI-generated texts using linguistic features automatically extracted from an online computational tool2024 · 12 citations