ML Research Wiki / Benchmarks / Fake News Detection / FNC-1

FNC-1

Fake News Detection Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: Weighted Accuracy

Top Performing Models

Rank	Model	Paper	Weighted Accuracy	Date	Code
1	ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)	Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection	84.60	2022-10-15	-
2	Bhatt et al.	On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification	83.08	2017-12-11	📦 vineet2104/StanceDetection-CS626
3	Bi-LSTM (max-pooling, attention)	Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News	82.23	2018-11-02	📦 imran3180/pytorch-nli 📦 LuisPB7/fnc-msc 📦 yinghao1019/imdb_prac
4	3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)	A simple but tough-to-beat baseline for the Fake News Challenge stance detection task	81.72	2017-07-11	📦 uclnlp/fakenewschallenge 📦 uclmr/fakenewschallenge 📦 gabrielsaruhashi/anti-fake
5	Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)	Automatic Stance Detection Using End-to-End Memory Networks	81.23	2018-04-20	-
6	Neural method from Mohtarami et al. (Mohtarami et al., 2018)	Automatic Stance Detection Using End-to-End Memory Networks	78.97	2018-04-20	-
7	Baseline based on skip-thought embeddings (Bhatt et al., 2017)	On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification	76.18	2017-12-11	📦 vineet2104/StanceDetection-CS626
8	Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)	On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification	72.78	2017-12-11	📦 vineet2104/StanceDetection-CS626
9	Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) 📚	On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification	63.11	2017-12-11	📦 vineet2104/StanceDetection-CS626

All Papers (9)

Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection

2022

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

2017

Bhatt et al.

vineet2104/StanceDetection-CS626

Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News

2018

Bi-LSTM (max-pooling, attention)

imran3180/pytorch-nli LuisPB7/fnc-msc yinghao1019/imdb_prac

A simple but tough-to-beat baseline for the Fake News Challenge stance detection task

2017

3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)

uclnlp/fakenewschallenge uclmr/fakenewschallenge

Automatic Stance Detection Using End-to-End Memory Networks

2018

Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)

Automatic Stance Detection Using End-to-End Memory Networks

2018

Neural method from Mohtarami et al. (Mohtarami et al., 2018)

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

2017

Baseline based on skip-thought embeddings (Bhatt et al., 2017)

vineet2104/StanceDetection-CS626

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

2017

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

vineet2104/StanceDetection-CS626

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

2017

Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)

vineet2104/StanceDetection-CS626

FNC-1

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (9)

Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News

A simple but tough-to-beat baseline for the Fake News Challenge stance detection task

Automatic Stance Detection Using End-to-End Memory Networks

Automatic Stance Detection Using End-to-End Memory Networks

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification

Model	Paper	Weighted Accuracy	Date
ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)	Combination Of Convolution Neural Networks And De…	84.60	2022-10-15
Bhatt et al.	On the Benefit of Combining Neural, Statistical a…	83.08	2017-12-11
Bi-LSTM (max-pooling, attention)	Combining Similarity Features and Deep Representa…	82.23	2018-11-02
3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)	A simple but tough-to-beat baseline for the Fake …	81.72	2017-07-11
Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)	Automatic Stance Detection Using End-to-End Memor…	81.23	2018-04-20
Neural method from Mohtarami et al. (Mohtarami et al., 2018)	Automatic Stance Detection Using End-to-End Memor…	78.97	2018-04-20
Baseline based on skip-thought embeddings (Bhatt et al., 2017)	On the Benefit of Combining Neural, Statistical a…	76.18	2017-12-11
Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)	On the Benefit of Combining Neural, Statistical a…	72.78	2017-12-11
Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)	On the Benefit of Combining Neural, Statistical a…	63.11	2017-12-11