{"url":"/dataset/20newsgroups","name":"20NewsGroups","full_name":null,"description_markdown":"The 20 Newsgroups data set is a collection of approximately 20,000 newsgroup documents, partitioned (nearly) evenly across 20 different newsgroups.","description_withheld":null,"homepage":"http://qwone.com/~jason/20Newsgroups/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-comparison-of-svm-against-pre-trained","title":"A Comparison of SVM against Pre-trained Language Models (PLMs) for Text Classification Tasks","first_author":"Yasmen Wahba","url":null},"license":null,"modalities":[],"tasks":[{"name":"Intrusion Detection","url":"/task/intrusion-detection","datasets_with_task":"/datasets/task/intrusion-detection"},{"name":"Topic Models","url":"/task/topic-models","datasets_with_task":"/datasets/task/topic-models"},{"name":"Unsupervised Text Classification","url":"/task/unsupervised-text-classification","datasets_with_task":"/datasets/task/unsupervised-text-classification"}],"languages":[],"variants":["20NewsGroups"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/topic-models-on-20newsgroups","task":"Topic Models","dataset_variant":"20NewsGroups","rows":6,"metrics":["C_v"],"first_row_in_archive_order":{"model":"vONTSS","paper":"/paper/vontss-vmf-based-semi-supervised-neural-topic","metrics":{"C_v":"0.69"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-text-classification-on-1","task":"Unsupervised Text Classification","dataset_variant":"20NewsGroups","rows":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Lbl2Vec","paper":"/paper/lbl2vec-an-embedding-based-approach-for","metrics":{"F1-score":"75.1"},"code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/intrusion-detection-on-20newsgroups","task":"Intrusion Detection","dataset_variant":"20NewsGroups","rows":1,"metrics":["Actions Top-1 (S2)"],"first_row_in_archive_order":{"model":"intrusion detection","paper":"/paper/a-neural-network-architecture-combining-gated","metrics":{"Actions Top-1 (S2)":"action"},"code_links":[{"title":"AFAgarap/cnn-svm","url":"https://github.com/AFAgarap/cnn-svm"},{"title":"AFAgarap/malware-classification","url":"https://github.com/AFAgarap/malware-classification"},{"title":"AFAgarap/gru-svm","url":"https://github.com/AFAgarap/gru-svm"},{"title":"AFAgarap/wisconsin-breast-cancer","url":"https://github.com/AFAgarap/wisconsin-breast-cancer"},{"title":"da-moon/classifiers-monorepo","url":"https://github.com/da-moon/classifiers-monorepo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vontss-vmf-based-semi-supervised-neural-topic","title":"vONTSS: vMF based semi-supervised neural topic modeling with optimal transport","date":"2023-07-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lbl2vec-an-embedding-based-approach-for","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-sinkhorn-topic-model","title":"Neural Topic Model via Optimal Transport","date":"2020-08-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/topic-modeling-in-embedding-spaces","title":"Topic Modeling in Embedding Spaces","date":"2019-07-08","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":3,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spherical-latent-spaces-for-stable","title":"Spherical Latent Spaces for Stable Variational Autoencoders","date":"2018-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-neural-network-architecture-combining-gated","title":"A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data","date":"2017-09-10","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/discovering-discrete-latent-topics-with","title":"Discovering Discrete Latent Topics with Neural Variational Inference","date":"2017-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/autoencoding-variational-inference-for-topic","title":"Autoencoding Variational Inference For Topic Models","date":"2017-03-04","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":28,"samples_ran":5,"samples_unverified":23,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}