Table 1.
Vocabulary and sentence analysis of human- and ChatGPT-generated text in the medical abstract and radiology report data sets.
|
|
|
Vocabularya | Word stemsb | Sentences per sample, mean (SD) | Sentence length (words), mean (SD) | Text length (words), mean (SD) |
| Medical abstract data set | ||||||
|
|
Human | 22,889 | 16,195 | 8.7 (2.3) | 16.2 (10.5) | 146.3 (19.4) |
|
|
ChatGPT | 15,782 | 11,120 | 10.4 (2.5) | 15.7 (8.3) | 168.6 (27.2) |
| Radiology report data set | ||||||
|
|
Human | 11,095 | 8396 | 12.7 (2.6) | 10.4 (6.9) | 135.9 (19.5) |
|
|
ChatGPT | 7733 | 5774 | 12.5 (3.2) | 10.2 (5.7) | 130.5 (31.3) |
aTotal number of unique words across all samples.
bTotal number of unique word stems across all samples.