Table 3 Multi-mode experiments: xFakeSci performance evaluation for recent publications (2019- - 2024).
From: Detection of ChatGPT fake science with the xFakeSci learning algorithm
Classifier used | Disease dataset tested | TP | FP | FN | TN | F1 Score (%) |
|---|---|---|---|---|---|---|
xFakeSci | Depression | 50 | 25 | 0 | 25 | 80.00 |
xFakeSci | Cancer | 50 | 9 | 0 | 41 | 91.74 |
xFakeSci | Alzheimer’s | 50 | 12 | 0 | 38 | 89.29 |
