Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Fake News DetectiononFNC-1
Per-class Accuracy (Agree)· 2017-12-11
50.7
best: 88.47 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
SOTA
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification arXiv:1712.03935
Fake News DetectiononFNC-1
Per-class Accuracy (Disagree)· 2017-12-11
9.61
best: 96 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
SOTA
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification arXiv:1712.03935
Fake News DetectiononFNC-1
Per-class Accuracy (Discuss)· 2017-12-11
53.38
best: 87.7 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification arXiv:1712.03935
Fake News DetectiononFNC-1
Per-class Accuracy (Unrelated)· 2017-12-11
96.05
best: 99.36 (Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021))
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification arXiv:1712.03935
Fake News DetectiononFNC-1
Weighted Accuracy· 2017-12-11
72.78
best: 90.73 (Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021))
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification arXiv:1712.03935