{ "data_id": "43395", "name": "Disaster-Tweets", "exact_name": "Disaster-Tweets", "version": 1, "version_label": "v1.0", "description": "Context\nThe file contains over 11,000 tweets associated with disaster keywords like crash, quarantine, and bush fires as well as the location and keyword itself. The data structure was inherited from Disasters on social media\nThe tweets were collected on Jan 14th, 2020.\nSome of the topics people were tweeting:\n\nThe eruption of Taal Volcano in Batangas, Philippines\nCoronavirus\nBushfires in Australia\nIran downing of the airplane flight PS752\n\nDisclaimer: The dataset contains text that may be considered profane, vulgar, or offensive.\nInspiration\nThe intention was to enrich the already available data for this topic with newly collected and manually classified tweets.\nThe initial source Disasters on social media which is used in Real or Not? NLP with Disaster Tweets competition on Kaggle.", "format": "arff", "uploader": "Onur Yildirim", "uploader_id": 30126, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 12:57:34", "update_comment": null, "last_update": "2022-03-23 12:57:34", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102220\/dataset", "kaggle_url": null, "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Disaster-Tweets", "Context The file contains over 11,000 tweets associated with disaster keywords like crash, quarantine, and bush fires as well as the location and keyword itself. The data structure was inherited from Disasters on social media The tweets were collected on Jan 14th, 2020. Some of the topics people were tweeting: The eruption of Taal Volcano in Batangas, Philippines Coronavirus Bushfires in Australia Iran downing of the airplane flight PS752 Disclaimer: The dataset contains text that may be conside " ], "weight": 5 }, "qualities": { "NumberOfInstances": 11370, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 3535, "NumberOfInstancesWithMissingValues": 3535, "NumberOfNumericFeatures": 2, "NumberOfSymbolicFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 31.090589270008795, "PercentageOfMissingValues": 6.218117854001759, "AutoCorrelation": null, "PercentageOfNumericFeatures": 40, "Dimensionality": 0.00043975373790677223, "PercentageOfSymbolicFeatures": 0, "MajorityClassPercentage": null, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0 }, "tags": [], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "11370", "missing": "0", "min": "0", "max": "11369", "mean": "5685", "stdev": "3282" }, { "name": "keyword", "index": "1", "type": "string", "distinct": "219", "missing": "0" }, { "name": "location", "index": "2", "type": "string", "distinct": "4358", "missing": "3535" }, { "name": "text", "index": "3", "type": "string", "distinct": "11220", "missing": "0" }, { "name": "target", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }