{
    "data_id": "43850",
    "name": "Hatred-on-Twitter-During-MeToo-Movement",
    "exact_name": "Hatred-on-Twitter-During-MeToo-Movement",
    "version": 1,
    "version_label": "v1.0",
    "description": "Interest and Motivation\nThis dataset belongs to the MeToo movement on Twitter. This movement was against the sexual harassment incidents and many people posted various hatred tweets. Using this dataset, we can build a model that can accurately classify hatred and non-hatred tweets to restrict its spread.\nDataset Description\nThe details about the columns are as follows:\n\nstatus_id: A unique id for each tweet [numeric].\ntext: tweet text data [string].\ncreated_at: The timestamp of the tweet [timestamp].\nfavourite_count: favourite count of the user of the tweet [numeric].\nretweet_count: retweet count of the tweet [numeric].\nlocation: location mentioned by the user while tweeting [string].\nfollowers_count: user's followers' count [numeric].\nfriends_count: user's friends' count [numeric].\nstatuses_count: user's total statuses count [numeric].\ncategory: target variable, whether tweet belongs to hatred (category=1) or non-hatred (catogory=0).",
    "format": "arff",
    "uploader": "Elif Ceren Gok",
    "uploader_id": 30125,
    "visibility": "public",
    "creator": null,
    "contributor": null,
    "date": "2022-03-24 15:45:46",
    "update_comment": null,
    "last_update": "2022-03-24 15:45:46",
    "licence": "CC BY-NC-SA 4.0",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/22102675\/dataset",
    "kaggle_url": null,
    "default_target_attribute": null,
    "row_id_attribute": null,
    "ignore_attribute": "\"status_id\"",
    "runs": 0,
    "suggest": {
        "input": [
            "Hatred-on-Twitter-During-MeToo-Movement",
            "Interest and Motivation This dataset belongs to the MeToo movement on Twitter. This movement was against the sexual harassment incidents and many people posted various hatred tweets. Using this dataset, we can build a model that can accurately classify hatred and non-hatred tweets to restrict its spread. Dataset Description The details about the columns are as follows: status_id: A unique id for each tweet [numeric]. text: tweet text data [string]. created_at: The timestamp of the tweet [timesta "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 807174,
        "NumberOfFeatures": 9,
        "NumberOfClasses": null,
        "NumberOfMissingValues": 197782,
        "NumberOfInstancesWithMissingValues": 196797,
        "NumberOfNumericFeatures": 6,
        "NumberOfSymbolicFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 24.380988485754003,
        "PercentageOfMissingValues": 2.7225576861714793,
        "AutoCorrelation": null,
        "PercentageOfNumericFeatures": 66.66666666666666,
        "Dimensionality": 1.1150012265013491e-5,
        "PercentageOfSymbolicFeatures": 0,
        "MajorityClassPercentage": null,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 0
    },
    "tags": [],
    "features": [
        {
            "name": "status_id",
            "index": "0",
            "type": "numeric",
            "distinct": "807169",
            "missing": "0",
            "ignore": "1",
            "min": "2147483647",
            "max": "2147483647",
            "mean": "2147483647",
            "stdev": "2147483647"
        },
        {
            "name": "text",
            "index": "1",
            "type": "string",
            "distinct": "694198",
            "missing": "3596"
        },
        {
            "name": "created_at",
            "index": "2",
            "type": "string",
            "distinct": "746663",
            "missing": "0"
        },
        {
            "name": "favorite_count",
            "index": "3",
            "type": "numeric",
            "distinct": "1401",
            "missing": "0",
            "min": "0",
            "max": "70385",
            "mean": "6",
            "stdev": "160"
        },
        {
            "name": "retweet_count",
            "index": "4",
            "type": "numeric",
            "distinct": "886",
            "missing": "0",
            "min": "0",
            "max": "17484",
            "mean": "3",
            "stdev": "51"
        },
        {
            "name": "location",
            "index": "5",
            "type": "string",
            "distinct": "74595",
            "missing": "194186"
        },
        {
            "name": "followers_count",
            "index": "6",
            "type": "numeric",
            "distinct": "47119",
            "missing": "0",
            "min": "0",
            "max": "54576429",
            "mean": "46638",
            "stdev": "611181"
        },
        {
            "name": "friends_count",
            "index": "7",
            "type": "numeric",
            "distinct": "22411",
            "missing": "0",
            "min": "0",
            "max": "899383",
            "mean": "6307",
            "stdev": "40550"
        },
        {
            "name": "statuses_count",
            "index": "8",
            "type": "numeric",
            "distinct": "113324",
            "missing": "0",
            "min": "1",
            "max": "9565126",
            "mean": "47936",
            "stdev": "164647"
        },
        {
            "name": "category",
            "index": "9",
            "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
}