Dataset Open Access
Johannes Kiesel;
Martin Potthast;
Maria Mestre;
Rishabh Shukla;
Benno Stein;
David Corney;
Emmanuel Vincent;
Payam Adineh
{ "files": [ { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/articles-training-20180831.xml.zip" }, "checksum": "md5:c3e85da69f0ec76d30a2c1a0b22d3150", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "articles-training-20180831.xml.zip", "type": "zip", "size": 1381470031 }, { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/articles-validation-20180831.xml.zip" }, "checksum": "md5:5dd17f5043f130407cf599d585ba4ca9", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "articles-validation-20180831.xml.zip", "type": "zip", "size": 547904088 }, { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/article.xsd" }, "checksum": "md5:31e3fb439c98b18cd74a7d936a65b218", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "article.xsd", "type": "xsd", "size": 2129 }, { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/ground-truth-training-20180831.xml.zip" }, "checksum": "md5:7ea315edde4f500b554571f388a2fa46", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "ground-truth-training-20180831.xml.zip", "type": "zip", "size": 29988422 }, { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/ground-truth-validation-20180831.xml.zip" }, "checksum": "md5:50fdbd01f9eef4902a0e6fe93a360577", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "ground-truth-validation-20180831.xml.zip", "type": "zip", "size": 6984845 }, { "links": { "self": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193/ground-truth.xsd" }, "checksum": "md5:81dd0e153d6f78ca10a5599da6aac66e", "bucket": "6c46d923-f702-4a89-90c5-ace2e9f85193", "key": "ground-truth.xsd", "type": "xsd", "size": 1628 } ], "owners": [ 65747 ], "doi": "10.5281/zenodo.1406208", "stats": { "version_unique_downloads": 5745.0, "unique_views": 8432.0, "views": 8932.0, "version_views": 21135.0, "unique_downloads": 550.0, "version_unique_views": 17168.0, "volume": 982677822957.0, "version_downloads": 24031.0, "downloads": 1952.0, "version_volume": 10610323270275.0 }, "links": { "doi": "https://doi.org/10.5281/zenodo.1406208", "conceptdoi": "https://doi.org/10.5281/zenodo.1310145", "bucket": "https://zenodo.org/api/files/6c46d923-f702-4a89-90c5-ace2e9f85193", "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.1310145.svg", "html": "https://zenodo.org/record/1406208", "latest_html": "https://zenodo.org/record/5776081", "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.1406208.svg", "latest": "https://zenodo.org/api/records/5776081" }, "conceptdoi": "10.5281/zenodo.1310145", "created": "2018-09-02T22:06:52.730331+00:00", "updated": "2021-12-13T11:13:05.909769+00:00", "conceptrecid": "1310145", "revision": 21, "id": 1406208, "metadata": { "access_right_category": "success", "doi": "10.5281/zenodo.1406208", "description": "<p>Third trial dataset for the SemEval 2019 Task 4: Hyperpartisan News Detection.</p>\n\n<p>The dataset contains 1 million articles. It is split in training (200,000 left, 400,000 least, 200,000 right) and validation (50,000 left, 100,000 least, 50,000 right), where <strong>no</strong> publisher that occurs in the training set also occurs in the validation set. All articles are labeled by the overall bias of the publisher as provided by BuzzFeed journalists or MediaBiasFactCheck.com.</p>\n\n<p>The trial data is not fully cleaned. Due to some encoding error, some characters are replaced by question marks. However, all files are already fully compatible with the XML schema files.</p>", "language": "eng", "title": "SemEval 2019 Task 4 - Hyperpartisan News Detection", "license": { "id": "CC-BY-4.0" }, "relations": { "version": [ { "count": 6, "index": 3, "parent": { "pid_type": "recid", "pid_value": "1310145" }, "is_last": false, "last_child": { "pid_type": "recid", "pid_value": "5776081" } } ] }, "communities": [ { "id": "pan" }, { "id": "webis" } ], "version": "Trial v3", "keywords": [ "Hyperpartisan news", "SemEval", "SemEval 2019", "SemEval 2019 Task 4", "Biased news", "News bias", "Hyperpartisan", "Hyperpartisanship" ], "publication_date": "2018-09-03", "creators": [ { "orcid": "0000-0002-1617-6508", "affiliation": "Bauhaus-Universit\u00e4t Weimar", "name": "Johannes Kiesel" }, { "affiliation": "Leipzig University", "name": "Martin Potthast" }, { "affiliation": "Factmata Ltd.", "name": "Maria Mestre" }, { "affiliation": "Factmata Ltd.", "name": "Rishabh Shukla" }, { "affiliation": "Bauhaus-Universit\u00e4t Weimar", "name": "Benno Stein" }, { "name": "David Corney" }, { "affiliation": "Factmata Ltd.", "name": "Emmanuel Vincent" }, { "affiliation": "Bauhaus-Universit\u00e4t Weimar", "name": "Payam Adineh" } ], "meeting": { "acronym": "SemEval-2019", "url": "http://alt.qcri.org/semeval2019/", "session": "Task 4", "title": "International Workshop on Semantic Evaluation 2019" }, "access_right": "open", "resource_type": { "type": "dataset", "title": "Dataset" }, "related_identifiers": [ { "scheme": "url", "identifier": "https://pan.webis.de/semeval19/semeval19-web/", "relation": "isReferencedBy" }, { "scheme": "doi", "identifier": "10.5281/zenodo.1310145", "relation": "isVersionOf" } ] } }
All versions | This version | |
---|---|---|
Views | 21,135 | 8,932 |
Downloads | 24,031 | 1,952 |
Data volume | 10.6 TB | 982.7 GB |
Unique views | 17,168 | 8,432 |
Unique downloads | 5,745 | 550 |