{"id":5082,"identifier":"DVN/C0DGSS","persistentUrl":"https://doi.org/10.34934/DVN/C0DGSS","protocol":"doi","authority":"10.34934","publisher":"Social Sciences and Digital Humanities Archive – SODHA","publicationDate":"2025-08-26","storageIdentifier":"file://10.34934/DVN/C0DGSS","datasetVersion":{"id":698,"datasetId":5082,"datasetPersistentId":"doi:10.34934/DVN/C0DGSS","storageIdentifier":"file://10.34934/DVN/C0DGSS","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","UNF":"UNF:6:V1hHFXDQD/rmLVuNusTOTg==","lastUpdateTime":"2025-08-26T14:19:44Z","releaseTime":"2025-08-26T14:19:44Z","createTime":"2025-08-26T14:09:06Z","termsOfUse":"<a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\"><img alt=\"Creative Commons License\" style=\"border-width:0\" src=\"https://i.creativecommons.org/l/by/4.0/88x31.png\" /></a><br />This work is licensed under a <a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\">Creative Commons Attribution 4.0 International License</a> (CC-BY).","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Seed lists for BelgicaWeb research project related to the archiving of web and social media content"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Geeraert, Friedel"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"KBR"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-5780-2763"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Vandendyck, Christina"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"KBR"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Geeraert, Friedel"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"KBR"}},{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Vandendyck, Christina"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"KBR"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"These spreadsheets are part of the research data produced within the BelgicaWeb project. It is a BRAIN 2.0 project funded by BELSPO (2024-2026). BelgicaWeb aims to make Belgium’s born-digital heritage accessible and FAIR, i.e. Findable, Accessible, Interoperable and Reusable by developing a user-friendly access platform and an API that enables access at data level. The spreadsheets list the seeds that were given to the Browsertrix crawler software to create a corpus of archived web and social media content."}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities","Computer and Information Science"]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassVocab":{"typeName":"topicClassVocab","multiple":false,"typeClass":"primitive","value":"CESSDA Topic Classification"},"topicClassVocabURI":{"typeName":"topicClassVocabURI","multiple":false,"typeClass":"primitive","value":"https://vocabularies.cessda.eu/vocabulary/TopicClassification"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Geeraert, Friedel"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2025-08-26"}]}},"files":[{"label":"20250825_full_list_PROMISE.tab","restricted":false,"version":3,"datasetVersionId":698,"dataFile":{"id":5084,"persistentId":"","pidURL":"","filename":"20250825_full_list_PROMISE.tab","contentType":"text/tab-separated-values","filesize":126284,"storageIdentifier":"file://198e6b5d7ca-748ef55e2f66","originalFileFormat":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","originalFormatLabel":"MS Excel Spreadsheet","originalFileSize":73336,"originalFileName":"20250825_full_list_PROMISE.xlsx","UNF":"UNF:6:aZGbFBi6llFhObvC7/O2CA==","rootDataFileId":-1,"md5":"f85b6caf7a7c81a87be04dfef7f73a35","checksum":{"type":"MD5","value":"f85b6caf7a7c81a87be04dfef7f73a35"},"creationDate":"2025-08-26"}},{"label":"20250826_full_list_BESOCIAL.tab","restricted":false,"version":3,"datasetVersionId":698,"dataFile":{"id":5083,"persistentId":"","pidURL":"","filename":"20250826_full_list_BESOCIAL.tab","contentType":"text/tab-separated-values","filesize":57310,"storageIdentifier":"file://198e6b5d88e-d95d2d1c1183","originalFileFormat":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","originalFormatLabel":"MS Excel Spreadsheet","originalFileSize":43313,"originalFileName":"20250826_full_list_BESOCIAL.xlsx","UNF":"UNF:6:9BmPTzS+0mtyHBdIWLBRBQ==","rootDataFileId":-1,"md5":"cbfb0c542361d822f07ca5aff508db8e","checksum":{"type":"MD5","value":"cbfb0c542361d822f07ca5aff508db8e"},"creationDate":"2025-08-26"}}],"citation":"Geeraert, Friedel; Vandendyck, Christina, 2025, \"Seed lists for BelgicaWeb research project related to the archiving of web and social media content\", https://doi.org/10.34934/DVN/C0DGSS, Social Sciences and Digital Humanities Archive – SODHA, V1, UNF:6:V1hHFXDQD/rmLVuNusTOTg== [fileUNF]"}}