{"id":"https://openalex.org/W3206643147","doi":"https://doi.org/10.5281/zenodo.3250070","title":"Paderborn Genre Analysis Corpus 2012 (PaGA-12)","display_name":"Paderborn Genre Analysis Corpus 2012 (PaGA-12)","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W3206643147","doi":"https://doi.org/10.5281/zenodo.3250070","mag":"3206643147"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/8398229","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083101824","display_name":"Micha\u00ebl Baumann","orcid":"https://orcid.org/0000-0002-9340-974X"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Baumann, Michael","raw_affiliation_strings":["Universit\u00e4t Paderborn"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Paderborn","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114253716","display_name":"Theodor Lettmann","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lettmann, Theodor","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stein, Benno","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083101824"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"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":{"id":"https://openalex.org/T12373","display_name":"Linguistic research and analysis","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12373","display_name":"Linguistic research and analysis","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13173","display_name":"Gender Studies in Language","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5178280472755432},{"id":"https://openalex.org/keywords/genre-analysis","display_name":"Genre analysis","score":0.48346930742263794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47780686616897583},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4317830801010132},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3448050916194916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.30991554260253906},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10717242956161499}],"concepts":[{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5178280472755432},{"id":"https://openalex.org/C2983877603","wikidata":"https://www.wikidata.org/wiki/Q5533546","display_name":"Genre analysis","level":2,"score":0.48346930742263794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47780686616897583},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4317830801010132},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3448050916194916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30991554260253906},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10717242956161499}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/8398229","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:zenodo.org:3250070","is_oa":true,"landing_page_url":"https://zenodo.org/record/3250070","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3250070","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3250070","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":"pmh:oai:figshare.com:article/8398229","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2352058714","https://openalex.org/W2337443140","https://openalex.org/W2075138115","https://openalex.org/W2624516427","https://openalex.org/W2290857006","https://openalex.org/W2943302606","https://openalex.org/W165798053","https://openalex.org/W4312969472"],"abstract_inverted_index":{"The":[0,53],"Paderborn":[1],"Genre":[2],"Analysis":[3],"2012":[4],"corpus":[5,36,54],"(PaGA-12)":[6],"contains":[7],"1,639":[8],"HTML":[9,43],"documents":[10,15,44],"of":[11,59],"26":[12],"genres.":[13],"All":[14,42],"were":[16],"collected":[17],"from":[18],"2009-10-18":[19],"to":[20,28],"2009-11-20,":[21],"and":[22,49],"each":[23,33],"document":[24],"is":[25,55,67],"manually":[26],"assigned":[27],"exactly":[29],"one":[30],"genre.":[31],"For":[32],"genre,":[34],"the":[35,64,75],"provides":[37],"at":[38],"least":[39],"50":[40],"documents.":[41],"contain":[45],"German":[46],"text":[47],"only,":[48],"framesets":[50],"are":[51],"removed.":[52],"delivered":[56,73],"in":[57,69],"form":[58],"a":[60,70],"MySQL":[61],"database":[62,65],"dump;":[63],"structure":[66],"detailed":[68],"README":[71],"file":[72],"with":[74],"corpus.":[76]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
