{"id":"https://openalex.org/W7131877518","doi":"https://doi.org/10.5281/zenodo.18807499","title":"Cross-Lingual YouTube Metadata with AI Topic Labels (English and Portuguese)","display_name":"Cross-Lingual YouTube Metadata with AI Topic Labels (English and Portuguese)","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7131877518","doi":"https://doi.org/10.5281/zenodo.18807499"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18807499","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18807499","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18807499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111128805","display_name":"M. Moacyrde Vasconcelos","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vasconcelos, Marisa","raw_affiliation_strings":["Universidade Federal de Minas Gerais"],"raw_orcid":"https://orcid.org/0000-0002-1366-6499","affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124262807","display_name":"Giovana A. M. Machado","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Machado, Giovana","raw_affiliation_strings":["Universidade Federal de Minas Gerais"],"raw_orcid":"https://orcid.org/0009-0004-7911-6504","affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065558693","display_name":"Costa Ip","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Costa, Igor","raw_affiliation_strings":["Universidade Federal de Minas Gerais"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036633153","display_name":"J. Almeida","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Almeida, Jussara","raw_affiliation_strings":["Universidade Federal de Minas Gerais"],"raw_orcid":"https://orcid.org/0000-0001-9142-2919","affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7868000268936157},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.753600001335144},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.36149999499320984},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.35910001397132874},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3481000065803528},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7868000268936157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.753600001335144},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6366000175476074},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5156000256538391},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C2982933515","wikidata":"https://www.wikidata.org/wiki/Q104381823","display_name":"Public access","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18807499","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18807499","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18807499","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18807499","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"dataset":[1,101],"contains":[2],"metadata":[3],"and":[4,15,35,110,125],"topic":[5,37,73,81,86,90,123],"annotations":[6],"for":[7,116],"AI-related":[8,120],"YouTube":[9,54],"videos":[10],"collected":[11],"in":[12],"English":[13],"(USA)":[14],"Portuguese":[16],"(Brazil).":[17],"The":[18,100],"data":[19],"was":[20],"curated":[21],"through":[22],"a":[23],"multi-stage":[24],"pipeline":[25],"including":[26],"transcript":[27],"retrieval,":[28],"large":[29],"language":[30],"model-based":[31],"screening,":[32],"human":[33],"validation,":[34],"supervised":[36],"classification.":[38],"Two":[39],"parquet":[40],"files":[41],"are":[42],"provided:":[43],"videos_usa.parquet":[44],"videos_brazil.parquet":[45],"Each":[46],"file":[47],"includes":[48],"the":[49,77],"following":[50],"fields:":[51],"VideoId:":[52],"Unique":[53,64],"video":[55,78],"identifier":[56,66],"Title:":[57],"Video":[58,68,93],"title":[59],"PublishedAt:":[60],"Publication":[61],"date":[62],"ChannelId:":[63],"channel":[65],"Duration:":[67],"duration":[69],"topics_list:":[70],"List":[71,84],"of":[72,85,128],"indexes":[74],"assigned":[75],"to":[76,108],"topic:":[79],"Dominant":[80,89],"index":[82],"topics_list_name:":[83],"labels":[87],"topic_name:":[88],"label":[91],"video_type:":[92],"format":[94],"category":[95],"(e.g.,":[96],"short-form":[97],"or":[98],"medium-length)":[99],"does":[102],"not":[103],"include":[104],"raw":[105],"transcripts":[106],"due":[107],"copyright":[109],"privacy":[111],"restrictions.":[112],"It":[113],"is":[114],"intended":[115],"academic":[117],"research":[118],"on":[119],"content,":[121],"cross-lingual":[122],"modeling,":[124],"temporal":[126],"analysis":[127],"online":[129],"discourse":[130]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-28T00:00:00"}
