Answers are grounded in this paper and cite their sources.
Comparative study of word frequencies distinguishes AI-generated texts from human-written essays, highlighting vocabulary differences.
We classify texts using relative word frequencies. The task is to distinguish human-written texts from those generated by a computer using modern algorithms. We study two essay datasets, each containing an equal number of human-written and computer-generated essays. Studying Zipf diagrams shows that the generated texts have a significantly smaller vocabulary compared to human ones. However, the relative frequency of rare words (not included in the 1000 most common) does not allow us to confidently classify the texts. As additional features, we used the relative frequencies of the four most frequent words, as well as the ratio of the number of hapax legomena to the total number of different words. This feature allows to significantly improve the classification. Using these six features allows us to fairly confidently determine whether the text is computer-generated.
No takes yet. Share an insight, caveat, or question.
Kudryavtseva et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: