{"url":"/dataset/germs-at","name":"GerMS-AT","full_name":"GERMS-AT: A Sexism/Misogyny Dataset of Forum Comments from an Austrian Online Newspaper","description_markdown":"This dataset contains 7984 user comments from an Austrian online newspaper. The comments have been annotated by 4 or more out of 11 annotators as to how strong sexism/mysogyny is present in the comment. It was used in the GermEval 2024 Shared Task 1: GerMS-Detect to evaluate data-driven approaches to automatically detect sexism in user comments.\r\n\r\nThe dataset was introduced and described in Brigitte Krenn, Johann Petrak, Marina Kubina, and Christian Burger. 2024. Germs-at: A sexism/misogyny dataset of forum comments from an Austrian online newspaper. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7728–7739.\r\n\r\nThe data can be downloaded here: https://huggingface.co/datasets/ofai/GerMS-AT","description_withheld":null,"homepage":"https://huggingface.co/datasets/ofai/GerMS-AT","introduced_date":"2024-08-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"GermEval2024 Shared Task 1 Subtask 1","url":"/task/germeval2024-shared-task-1-subtask-1","datasets_with_task":"/datasets/task/germeval2024-shared-task-1-subtask-1"},{"name":"GermEval2024 Shared Task 1 Subtask 2","url":"/task/germeval2024-shared-task-1-subtask-2","datasets_with_task":"/datasets/task/germeval2024-shared-task-1-subtask-2"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["GerMS-AT"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/germeval2024-shared-task-1-subtask-1-on-germs","task":"GermEval2024 Shared Task 1 Subtask 1","dataset_variant":"GerMS-AT","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"mE5-large-SVM","paper":"/paper/detecting-sexism-in-german-online-newspaper","metrics":{"Macro F1":"0.597"},"code_links":[{"title":"dslaborg/germeval2024","url":"https://github.com/dslaborg/germeval2024"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/germeval2024-shared-task-1-subtask-2-on-germs","task":"GermEval2024 Shared Task 1 Subtask 2","dataset_variant":"GerMS-AT","rows":1,"metrics":["Jensen-Shannon distance"],"first_row_in_archive_order":{"model":"GBERT-large-SVM","paper":"/paper/detecting-sexism-in-german-online-newspaper","metrics":{"Jensen-Shannon distance":"0.301"},"code_links":[{"title":"dslaborg/germeval2024","url":"https://github.com/dslaborg/germeval2024"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/detecting-sexism-in-german-online-newspaper","title":"Detecting Sexism in German Online Newspaper Comments with Open-Source Text Embeddings (Team GDA, GermEval2024 Shared Task 1: GerMS-Detect, Subtasks 1 and 2, Closed Track)","date":"2024-09-16","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}