Fake News Detection on FNC-1

Metric: Per-class Accuracy (Agree) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Per-class Accuracy (Agree)▼	Extra Data	Paper	Date↕	Code
1	ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)	88.47	No	Combination Of Convolution Neural Networks And D...	2022-10-15	-
2	Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021)	75.03	No	-	-	Code
3	Bi-LSTM (max-pooling, attention)	51.34	No	Combining Similarity Features and Deep Represent...	2018-11-02	Code
4	Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)	50.7	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
5	3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)	44.04	No	A simple but tough-to-beat baseline for the Fake...	2017-07-11	Code
6	Bhatt et al.	43.82	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
7	Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)	38.04	Yes	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
8	Baseline based on skip-thought embeddings (Bhatt et al., 2017)	31.8	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code

#1ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)SOTA
88.47
Per-class Accuracy (Agree)· 2022-10-15
Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection
#2Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021)
75.03
Per-class Accuracy (Agree)
No paperCode
#3Bi-LSTM (max-pooling, attention)SOTA
51.34
Per-class Accuracy (Agree)· 2018-11-02
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News Code
#4Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)SOTA
50.7
Per-class Accuracy (Agree)· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#53rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)SOTA
44.04
Per-class Accuracy (Agree)· 2017-07-11
A simple but tough-to-beat baseline for the Fake News Challenge stance detection task Code
#6Bhatt et al.
43.82
Per-class Accuracy (Agree)· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#7Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)
38.04
Per-class Accuracy (Agree)· Extra Data· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#8Baseline based on skip-thought embeddings (Bhatt et al., 2017)
31.8
Per-class Accuracy (Agree)· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code