{"url":"/sota/fake-news-detection-on-fnc-1","task":{"name":"Fake News Detection","url":"/task/fake-news-detection","note":null},"dataset":{"name":"FNC-1","url":"/dataset/fnc-1"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Fake News Detection** is a natural language processing task that involves identifying and classifying news articles or other types of text as real or fake. The goal of fake news detection is to develop algorithms that can automatically identify and flag fake news articles, which can be used to combat misinformation and promote the dissemination of accurate information.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Weighted Accuracy","Per-class Accuracy (Unrelated)","Per-class Accuracy (Agree)","Per-class Accuracy (Disagree)","Per-class Accuracy (Discuss)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Weighted Accuracy":"higher","Per-class Accuracy (Unrelated)":"higher","Per-class Accuracy (Agree)":"higher","Per-class Accuracy (Disagree)":"higher","Per-class Accuracy (Discuss)":"higher"}},"counts":{"rows":10,"rows_with_code":7,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021)","metrics":{"Per-class Accuracy (Agree)":"75.03","Per-class Accuracy (Disagree)":"63.41","Per-class Accuracy (Discuss)":"85.97","Per-class Accuracy (Unrelated)":"99.36","Weighted Accuracy":"90.73"},"uses_additional_data":false,"paper_date":"2021-06-20","paper":"/paper/exploring-summarization-to-enhance-headline","paper_url":"https://link.springer.com/chapter/10.1007/978-3-030-80599-9_22","paper_title":"Exploring Summarization to Enhance Headline Stance Detection","code":"https://github.com/rsepulveda911112/Headline-Stance-Detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022)","metrics":{"Per-class Accuracy (Agree)":"88.47","Per-class Accuracy (Disagree)":"96.00","Per-class Accuracy (Discuss)":"87.70","Per-class Accuracy (Unrelated)":"95.04","Weighted Accuracy":"84.60"},"uses_additional_data":false,"paper_date":"2022-10-15","paper":"/paper/combination-of-convolution-neural-networks-1","paper_url":"https://arxiv.org/abs/2210.08331v1","paper_title":"Combination Of Convolution Neural Networks And Deep Neural Networks For Fake News Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Bhatt et al.","metrics":{"Per-class Accuracy (Agree)":"43.82","Per-class Accuracy (Disagree)":"6.31","Per-class Accuracy (Discuss)":"85.68","Per-class Accuracy (Unrelated)":"98.04","Weighted Accuracy":"83.08"},"uses_additional_data":false,"paper_date":"2017-12-11","paper":"/paper/on-the-benefit-of-combining-neural","paper_url":"http://arxiv.org/abs/1712.03935v1","paper_title":"On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification","code":"https://github.com/vineet2104/StanceDetection-CS626","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Bi-LSTM (max-pooling, attention)","metrics":{"Per-class Accuracy (Agree)":"51.34","Per-class Accuracy (Disagree)":"10.33","Per-class Accuracy (Discuss)":"81.52","Per-class Accuracy (Unrelated)":"96.74","Weighted Accuracy":"82.23"},"uses_additional_data":false,"paper_date":"2018-11-02","paper":"/paper/combining-similarity-features-and-deep","paper_url":"http://arxiv.org/abs/1811.00706v1","paper_title":"Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News","code":"https://github.com/imran3180/pytorch-nli","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)","metrics":{"Per-class Accuracy (Agree)":"44.04","Per-class Accuracy (Disagree)":"6.60","Per-class Accuracy (Discuss)":"81.38","Per-class Accuracy (Unrelated)":"97.90","Weighted Accuracy":"81.72"},"uses_additional_data":false,"paper_date":"2017-07-11","paper":"/paper/a-simple-but-tough-to-beat-baseline-for-the","paper_url":"http://arxiv.org/abs/1707.03264v2","paper_title":"A simple but tough-to-beat baseline for the Fake News Challenge stance detection task","code":"https://github.com/uclnlp/fakenewschallenge","n_code_links":9,"syntology":null},{"rank_in_archive_order":6,"model":"Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018)","metrics":{"Weighted Accuracy":"81.23"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/automatic-stance-detection-using-end-to-end","paper_url":"http://arxiv.org/abs/1804.07581v1","paper_title":"Automatic Stance Detection Using End-to-End Memory Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Neural method from Mohtarami et al. (Mohtarami et al., 2018)","metrics":{"Weighted Accuracy":"78.97"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/automatic-stance-detection-using-end-to-end","paper_url":"http://arxiv.org/abs/1804.07581v1","paper_title":"Automatic Stance Detection Using End-to-End Memory Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Baseline based on skip-thought embeddings (Bhatt et al., 2017)","metrics":{"Per-class Accuracy (Agree)":"31.80","Per-class Accuracy (Disagree)":"0.00","Per-class Accuracy (Discuss)":"81.20","Per-class Accuracy (Unrelated)":"91.18","Weighted Accuracy":"76.18"},"uses_additional_data":false,"paper_date":"2017-12-11","paper":"/paper/on-the-benefit-of-combining-neural","paper_url":"http://arxiv.org/abs/1712.03935v1","paper_title":"On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification","code":"https://github.com/vineet2104/StanceDetection-CS626","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Baseline based on word2vec + hand-crafted features (Bhatt et al., 2017)","metrics":{"Per-class Accuracy (Agree)":"50.70","Per-class Accuracy (Disagree)":"9.61","Per-class Accuracy (Discuss)":"53.38","Per-class Accuracy (Unrelated)":"96.05","Weighted Accuracy":"72.78"},"uses_additional_data":false,"paper_date":"2017-12-11","paper":"/paper/on-the-benefit-of-combining-neural","paper_url":"http://arxiv.org/abs/1712.03935v1","paper_title":"On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification","code":"https://github.com/vineet2104/StanceDetection-CS626","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Neural baseline based on bi-directional LSTMs (Bhatt et al., 2017)","metrics":{"Per-class Accuracy (Agree)":"38.04","Per-class Accuracy (Disagree)":"4.59","Per-class Accuracy (Discuss)":"58.132","Per-class Accuracy (Unrelated)":"78.27","Weighted Accuracy":"63.11"},"uses_additional_data":true,"paper_date":"2017-12-11","paper":"/paper/on-the-benefit-of-combining-neural","paper_url":"http://arxiv.org/abs/1712.03935v1","paper_title":"On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification","code":"https://github.com/vineet2104/StanceDetection-CS626","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}