Papers › On the Benefit of Combining Neural, Statistical and External Features for Fake News...
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
Gaurav Bhatt, Aman Sharma, Shivam Sharma, Ankush Nagpal, Balasubramanian Raman, Ankush Mittal
Identifying the veracity of a news article is an interesting problem while automating this process can be a challenging task. Detection of a news article as fake is still an open question as it is contingent on many factors which the current state-of-the-art models fail to incorporate. In this paper, we explore a subtask to fake news identification, and that is stance detection. Given a news article, the task is to determine the relevance of the body and its claim. We present a novel idea that combines the neural, statistical and external features to provide an efficient solution to this problem. We compute the neural embedding from the deep recurrent model, statistical features from the weighted n-gram bag-of-words model and handcrafted external features with the help of feature engineering heuristics. Finally, using deep neural layer all the features are combined, thereby classifying the headline-body news pair as agree, disagree, discuss, or unrelated. We compare our proposed technique with the current state-of-the-art models on the fake news challenge dataset. Through extensive experiments, we find that the proposed model outperforms all the state-of-the-art techniques including the submissions to the fake news challenge.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Fake News Detection | FNC-1 | Bhatt et al. | Per-class Accuracy (Agree) | 43.82 | #3 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Bhatt et al. | Per-class Accuracy (Disagree) | 6.31 | #3 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Bhatt et al. | Per-class Accuracy (Discuss) | 85.68 | #3 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Bhatt et al. | Per-class Accuracy (Unrelated) | 98.04 | #3 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Bhatt et al. | Weighted Accuracy | 83.08 | #3 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on skip-thought embeddings (Bhatt et al., 2017) | Per-class Accuracy (Agree) | 31.80 | #8 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on skip-thought embeddings (Bhatt et al., 2017) | Per-class Accuracy (Disagree) | 0.00 | #8 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on skip-thought embeddings (Bhatt et al., 2017) | Per-class Accuracy (Discuss) | 81.20 | #8 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on skip-thought embeddings (Bhatt et al., 2017) | Per-class Accuracy (Unrelated) | 91.18 | #8 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on skip-thought embeddings (Bhatt et al., 2017) | Weighted Accuracy | 76.18 | #8 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017) | Per-class Accuracy (Agree) | 50.70 | #9 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017) | Per-class Accuracy (Disagree) | 9.61 | #9 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017) | Per-class Accuracy (Discuss) | 53.38 | #9 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017) | Per-class Accuracy (Unrelated) | 96.05 | #9 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017) | Weighted Accuracy | 72.78 | #9 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) | Per-class Accuracy (Agree) | 38.04 | #10 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) | Per-class Accuracy (Disagree) | 4.59 | #10 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) | Per-class Accuracy (Discuss) | 58.132 | #10 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) | Per-class Accuracy (Unrelated) | 78.27 | #10 of 10 | Archive leaderboard | report |
| Fake News Detection | FNC-1 | Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017) | Weighted Accuracy | 63.11 | #10 of 10 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections