{"data":{"id":"10.6084/m9.figshare.4245035","type":"dois","attributes":{"doi":"10.6084/m9.figshare.4245035","prefix":"10.6084","suffix":"m9.figshare.4245035","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Halfaker, Aaron","nameType":"Personal","givenName":"Aaron","familyName":"Halfaker","affiliation":[],"nameIdentifiers":[{"schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-8907-6367","nameIdentifierScheme":"ORCID"}]},{"name":"Rogers, Jacob","nameType":"Personal","givenName":"Jacob","familyName":"Rogers","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"Deleted Wikipedia articles (spam/vandalism/attack)"}],"publisher":"figshare","container":{},"publicationYear":2019,"subjects":[{"subject":"200302 English Language","subjectScheme":"FOR"},{"subject":"FOS: Languages and literature","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Languages and literature","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"Language"},{"subject":"Linguistics"},{"subject":"Artificial Intelligence and Image Processing"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Computer and information sciences","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"80107 Natural Language Processing","subjectScheme":"FOR"}],"contributors":[],"dates":[{"date":"2016-11-21","dateType":"Created"},{"date":"2019-12-17","dateType":"Updated"},{"date":"2019","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["179170 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Zero v1.0 Universal","rightsUri":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc0-1.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This dataset contains a random sample of deleted articles from English Wikipedia were the reason was explicitly either spam, vandalism, or attack. 25 articles were sampled for each deletion reason for a total of 75 articles. Text of the articles was censored to remove identifying information. \u003cbr\u003eThe dataset contains the following columns:\u003cbr\u003e · page_title -- The title of the deleted page · rev_id -- The rev_id of the first revision · creation_timestamp -- The time that the page was created · archived -- 1 if the page was deleted, 0 if not (always 1) · draft_quality -- The deletion reason (spam|vandalism|attack) · censored_text -- The censored text of the deleted page\u003cbr\u003eCensored blocks are noted with a comment block in the censored_text column of the form \"Censored: [reason]([explanation])\" -- e.g. \"Censored: PII(phone number)\". \u003cbr\u003e\u003cbr\u003e","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://figshare.com/articles/dataset/Deleted_Wikipedia_articles_spam_vandalism_attack_/4245035/1","contentUrl":null,"metadataVersion":10,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2016-11-21T19:31:51.000Z","registered":"2016-11-21T19:31:51.000Z","published":"2019","updated":"2020-09-03T11:44:59.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.4245035","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}