Fake News Detection On Fnc 1
Metrics
Per-class Accuracy (Agree)
Per-class Accuracy (Disagree)
Per-class Accuracy (Discuss)
Per-class Accuracy (Unrelated)
Weighted Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Per-class Accuracy (Agree) | Per-class Accuracy (Disagree) | Per-class Accuracy (Discuss) | Per-class Accuracy (Unrelated) | Weighted Accuracy |
|---|---|---|---|---|---|
| exploring-summarization-to-enhance-headline | 75.03 | 63.41 | 85.97 | 99.36 | 90.73 |
| on-the-benefit-of-combining-neural | 31.80 | 0.00 | 81.20 | 91.18 | 76.18 |
| on-the-benefit-of-combining-neural | 38.04 | 4.59 | 58.132 | 78.27 | 63.11 |
| on-the-benefit-of-combining-neural | 50.70 | 9.61 | 53.38 | 96.05 | 72.78 |
| automatic-stance-detection-using-end-to-end | - | - | - | - | 81.23 |
| automatic-stance-detection-using-end-to-end | - | - | - | - | 78.97 |
| combining-similarity-features-and-deep | 51.34 | 10.33 | 81.52 | 96.74 | 82.23 |
| combination-of-convolution-neural-networks-1 | 88.47 | 96.00 | 87.70 | 95.04 | 84.60 |
| a-simple-but-tough-to-beat-baseline-for-the | 44.04 | 6.60 | 81.38 | 97.90 | 81.72 |
| on-the-benefit-of-combining-neural | 43.82 | 6.31 | 85.68 | 98.04 | 83.08 |