{"data":{"id":"10.6084/m9.figshare.4563973","type":"dois","attributes":{"doi":"10.6084/m9.figshare.4563973","prefix":"10.6084","suffix":"m9.figshare.4563973","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Nithum Thain","affiliation":[],"nameIdentifiers":[]},{"name":"Dixon, Lucas","nameType":"Personal","givenName":"Lucas","familyName":"Dixon","affiliation":[],"nameIdentifiers":[]},{"name":"Wulczyn, Ellery","nameType":"Personal","givenName":"Ellery","familyName":"Wulczyn","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"Wikipedia Talk Labels: Toxicity"}],"publisher":"figshare","container":{},"publicationYear":2017,"subjects":[{"subject":"80107 Natural Language Processing","subjectScheme":"FOR"},{"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":"170203 Knowledge Representation and Machine Learning","subjectScheme":"FOR"},{"subject":"FOS: Psychology","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Psychology","subjectScheme":"Fields of Science and Technology (FOS)"}],"contributors":[],"dates":[{"date":"2017-01-18","dateType":"Created"},{"date":"2017-02-22","dateType":"Updated"},{"date":"2017","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["114459887 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 data set includes over 100k labeled discussion comments from English Wikipedia. Each comment was labeled by multiple annotators via Crowdflower on whether it is a toxic or healthy contribution. We also include some demographic data for each crowd-worker. See our wiki for documentation of the schema of each file and our research paper for documentation on the data collection and modeling methodology. For a quick demo of how to use the data for model building and analysis, check out this ipython notebook.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://figshare.com/articles/dataset/Wikipedia_Talk_Labels_Toxicity/4563973","contentUrl":null,"metadataVersion":5,"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":"2017-01-18T23:54:47.000Z","registered":"2017-01-18T23:54:47.000Z","published":"2017","updated":"2020-09-02T19:29:37.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.4563973","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}