{ "data_id": "42907", "name": "youtube-spam-eminem", "exact_name": "youtube-spam-eminem", "version": 1, "version_label": "1", "description": "**Author**: Unknown \n**Source**: [UCI](https:\/\/archive.ics.uci.edu\/ml\/datasets\/YouTube+Spam+Collection) - 2017\n**Please cite***: [Paper](http:\/\/dcomp.sor.ufscar.br\/talmeida\/youtubespamcollection\/) \n\n**YouTube Spam Collection Eminem dataset**\n\nIt is a public set of comments collected for spam research. It has five datasets composed by 1,956 real messages extracted from five videos that were among the 10 most viewed on the collection period. This dataset only contains information about LMFAO. It consists of 245 spam entries and 203 ham entries, leading to a grand total of 448 samples.\n\n\n### Attribute information\n\nThe collection is composed by one CSV file per dataset, where each line has the following attributes: \n\nCOMMENT_ID,AUTHOR,DATE,CONTENT,TAG \n", "format": "arff", "uploader": "Meilina Reksoprodjo", "uploader_id": 24140, "visibility": "public", "creator": "\"unknown\"", "contributor": null, "date": "2021-05-19 19:41:17", "update_comment": null, "last_update": "2021-05-19 19:41:17", "licence": "CC-BY", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22045538\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "youtube-spam-eminem", "It is a public set of comments collected for spam research. It has five datasets composed by 1,956 real messages extracted from five videos that were among the 10 most viewed on the collection period. This dataset only contains information about LMFAO. It consists of 245 spam entries and 203 ham entries, leading to a grand total of 448 samples. ### Attribute information The collection is composed by one CSV file per dataset, where each line has the following attributes: COMMENT_ID,AUTHOR,DATE,CO " ], "weight": 5 }, "qualities": { "NumberOfInstances": 448, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 245, "NumberOfInstancesWithMissingValues": 245, "NumberOfNumericFeatures": 1, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.011160714285714286, "PercentageOfNumericFeatures": 20, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 54.6875, "AutoCorrelation": null, "PercentageOfMissingValues": 10.9375 }, "tags": [ { "uploader": "38960", "tag": "Manufacturing" } ], "features": [ { "name": "COMMENT_ID", "index": "0", "type": "string", "distinct": "446", "missing": "0" }, { "name": "AUTHOR", "index": "1", "type": "string", "distinct": "392", "missing": "0" }, { "name": "DATE", "index": "2", "type": "string", "distinct": "203", "missing": "245" }, { "name": "CONTENT", "index": "3", "type": "string", "distinct": "412", "missing": "0" }, { "name": "CLASS", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "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 }