Fake News Detection on FNC-1

Metric: Weighted Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Weighted Accuracy▼	Extra Data	Paper	Date↕	Code
1	Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021)	90.73	No	-	-	Code
2	ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)	84.6	No	Combination Of Convolution Neural Networks And D...	2022-10-15	-
3	Bhatt et al.	83.08	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
4	Bi-LSTM (max-pooling, attention)	82.23	No	Combining Similarity Features and Deep Represent...	2018-11-02	Code
5	3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)	81.72	No	A simple but tough-to-beat baseline for the Fake...	2017-07-11	Code
6	Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)	81.23	No	Automatic Stance Detection Using End-to-End Memo...	2018-04-20	-
7	Neural method from Mohtarami et al. (Mohtarami et al., 2018)	78.97	No	Automatic Stance Detection Using End-to-End Memo...	2018-04-20	-
8	Baseline based on skip-thought embeddings (Bhatt et al., 2017)	76.18	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
9	Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)	72.78	No	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code
10	Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)	63.11	Yes	On the Benefit of Combining Neural, Statistical ...	2017-12-11	Code

#1Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021)
90.73
Weighted Accuracy
No paperCode
#2ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)SOTA
84.6
Weighted Accuracy· 2022-10-15
Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection
#3Bhatt et al.SOTA
83.08
Weighted Accuracy· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#4Bi-LSTM (max-pooling, attention)
82.23
Weighted Accuracy· 2018-11-02
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News Code
#53rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)SOTA
81.72
Weighted Accuracy· 2017-07-11
A simple but tough-to-beat baseline for the Fake News Challenge stance detection task Code
#6Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)
81.23
Weighted Accuracy· 2018-04-20
Automatic Stance Detection Using End-to-End Memory Networks
#7Neural method from Mohtarami et al. (Mohtarami et al., 2018)
78.97
Weighted Accuracy· 2018-04-20
Automatic Stance Detection Using End-to-End Memory Networks
#8Baseline based on skip-thought embeddings (Bhatt et al., 2017)
76.18
Weighted Accuracy· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#9Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)
72.78
Weighted Accuracy· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code
#10Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)
63.11
Weighted Accuracy· Extra Data· 2017-12-11
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification Code