{"url":"/dataset/web-of-science-dataset","name":"WOS","full_name":"Web of Science Dataset","description_markdown":"Web of Science (WOS) is a document classification dataset that contains 46,985 documents with 134 categories which include 7 parents categories.\r\n\r\nSource: [HDLTex: Hierarchical Deep Learning for Text Classification](/paper/hdltex-hierarchical-deep-learning-for-text)","description_withheld":null,"homepage":"https://data.mendeley.com/datasets/9rw3vkcfy4/6","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/hdltex-hierarchical-deep-learning-for-text","title":"HDLTex: Hierarchical Deep Learning for Text Classification","first_author":"Kamran Kowsari","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"},{"name":"Hierarchical Multi-label Classification","url":"/task/hierarchical-multi-label-classification","datasets_with_task":"/datasets/task/hierarchical-multi-label-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WOS-11967","WOS-46985","WOS-5736","WOS"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/HDLTex/web_of_science","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/web_of_science","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":59,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hierarchical-multi-label-classification-on-16","task":"Hierarchical Multi-label Classification","dataset_variant":"WOS","rows":3,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"HILL","paper":"/paper/hill-hierarchy-aware-information-lossless","metrics":{"Macro F1":"81.77","Micro F1":"87.28"},"code_links":[{"title":"rooooyy/hill","url":"https://github.com/rooooyy/hill"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-classification-on-wos-5736","task":"Document Classification","dataset_variant":"WOS-5736","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ConvTextTM","paper":"/paper/convtexttm-an-explainable-convolutional","metrics":{"Accuracy":"91.28"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-classification-on-wos-11967","task":"Document Classification","dataset_variant":"WOS-11967","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HDLTex","paper":"/paper/hdltex-hierarchical-deep-learning-for-text","metrics":{"Accuracy":"86.07"},"code_links":[{"title":"kk7nc/HDLTex","url":"https://github.com/kk7nc/HDLTex"},{"title":"lackel/hierarchical_weighted_scl","url":"https://github.com/lackel/hierarchical_weighted_scl"},{"title":"Lackel/DNA","url":"https://github.com/Lackel/DNA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-classification-on-wos-46985","task":"Document Classification","dataset_variant":"WOS-46985","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HDLTex","paper":"/paper/hdltex-hierarchical-deep-learning-for-text","metrics":{"Accuracy":"76.58"},"code_links":[{"title":"kk7nc/HDLTex","url":"https://github.com/kk7nc/HDLTex"},{"title":"lackel/hierarchical_weighted_scl","url":"https://github.com/lackel/hierarchical_weighted_scl"},{"title":"Lackel/DNA","url":"https://github.com/Lackel/DNA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hill-hierarchy-aware-information-lossless","title":"HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification","date":"2024-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hitin-hierarchy-aware-tree-isomorphism","title":"HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification","date":"2023-05-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":13,"samples_unverified":4,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convtexttm-an-explainable-convolutional","title":"ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification","date":"2022-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hdltex-hierarchical-deep-learning-for-text","title":"HDLTex: Hierarchical Deep Learning for Text Classification","date":"2017-09-24","rows_on_this_dataset":3,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":20,"samples_ran":16,"samples_unverified":4,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":0,"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."}