{"id":"https://openalex.org/W7204180424","doi":"https://doi.org/10.5281/zenodo.21904642","title":"Das Heftroman-Korpus: 437 Millionen Token deutscher Unterhaltungsliteratur als abgeleitete Textformate","display_name":"Das Heftroman-Korpus: 437 Millionen Token deutscher Unterhaltungsliteratur als abgeleitete Textformate","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204180424","doi":"https://doi.org/10.5281/zenodo.21904642"},"language":"de","primary_location":{"id":"doi:10.5281/zenodo.21904642","doi":"https://doi.org/10.5281/zenodo.21904642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21904642","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.21904642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125971425","display_name":"Deutsche Nationalbibliothek","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deutsche Nationalbibliothek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071676071","display_name":"Leonard Konle","orcid":"https://orcid.org/0000-0001-5833-0414","observed_orcids":["https://orcid.org/0000-0001-5833-0414"]},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konle, Leonard","raw_affiliation_strings":["University of W\u00fcrzburg"],"raw_orcid":"https://orcid.org/0000-0001-5833-0414","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052850851","display_name":"Fotis Jannidis","orcid":"https://orcid.org/0000-0001-6944-6113","observed_orcids":["https://orcid.org/0000-0001-6944-6113"]},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jannidis, Fotis","raw_affiliation_strings":["University of W\u00fcrzburg"],"raw_orcid":"https://orcid.org/0000-0001-6944-6113","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052738767","display_name":"Peter Leinen","orcid":"https://orcid.org/0000-0002-3014-000X","observed_orcids":["https://orcid.org/0000-0002-3014-000X","https://orcid.org/0009-0006-6233-8797"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leinen, Peter","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt"],"raw_orcid":"https://orcid.org/0000-0002-3014-000X","affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101154880","display_name":"Keli Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I89864525","display_name":"Universit\u00e4t Trier","ror":"https://ror.org/02778hg05","country_code":"DE","type":"education","lineage":["https://openalex.org/I89864525"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Du, Keli","raw_affiliation_strings":["Universit\u00e4t Trier"],"raw_orcid":"https://orcid.org/0000-0001-7800-0682","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Trier","institution_ids":["https://openalex.org/I89864525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089146605","display_name":"Christof Sch\u00f6ch","orcid":"https://orcid.org/0000-0002-4557-2753","observed_orcids":["https://orcid.org/0000-0002-4557-2753"]},"institutions":[{"id":"https://openalex.org/I89864525","display_name":"Universit\u00e4t Trier","ror":"https://ror.org/02778hg05","country_code":"DE","type":"education","lineage":["https://openalex.org/I89864525"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sch\u00f6ch, Christof","raw_affiliation_strings":["Universit\u00e4t Trier"],"raw_orcid":"https://orcid.org/0000-0002-4557-2753","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Trier","institution_ids":["https://openalex.org/I89864525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067326448","display_name":"Leander Seige","orcid":"https://orcid.org/0000-0002-7410-1336","observed_orcids":["https://orcid.org/0000-0002-7410-1336"]},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Seige, Leander","raw_affiliation_strings":["seige.digital GbR","Universit\u00e4t Leipzig Universit\u00e4tsbibliothek Leipzig"],"raw_orcid":"https://orcid.org/0000-0002-7410-1336","affiliations":[{"raw_affiliation_string":"seige.digital GbR","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e4t Leipzig Universit\u00e4tsbibliothek Leipzig","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138220334","display_name":"Philippe Gen\u00eat","orcid":"https://orcid.org/0009-0001-5095-8052","observed_orcids":["https://orcid.org/0009-0001-5095-8052"]},"institutions":[{"id":"https://openalex.org/I4210110517","display_name":"Deutsche Nationalbibliothek","ror":"https://ror.org/01n7gem85","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210110517"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gen\u00eat, Philippe","raw_affiliation_strings":["Deutsche Nationalbibliothek"],"raw_orcid":"https://orcid.org/0009-0001-5095-8052","affiliations":[{"raw_affiliation_string":"Deutsche Nationalbibliothek","institution_ids":["https://openalex.org/I4210110517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.6664999723434448,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.6664999723434448,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.20890000462532043,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.04100000113248825,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/german-popular-literature","display_name":"German popular literature","score":0.5870000123977661},{"id":"https://openalex.org/keywords/text-annotation","display_name":"textual annotation","score":0.38499999046325684},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.5049999952316284},{"id":"https://openalex.org/keywords/named-entities","display_name":"named entities","score":0.6650000214576721},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.7319999933242798},{"id":"https://openalex.org/keywords/bag-of-words","display_name":"bag-of-words","score":0.6399999856948853},{"id":"https://openalex.org/keywords/text-summarization","display_name":"text summarization","score":0.7549999952316284},{"id":"https://openalex.org/keywords/german-national-library","display_name":"German National Library","score":0.5559999942779541},{"id":"https://openalex.org/keywords/copyright-limitations","display_name":"copyright restrictions","score":0.41600000858306885},{"id":"https://openalex.org/keywords/literary-corpus","display_name":"literary corpus","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.31690001487731934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2581999897956848},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2232999950647354},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.1907999962568283},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.17110000550746918},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.14390000700950623},{"id":"https://openalex.org/C3019684712","wikidata":"https://www.wikidata.org/wiki/Q2280635","display_name":"Displacement method","level":2,"score":0.13809999823570251},{"id":"https://openalex.org/C3018844941","wikidata":"https://www.wikidata.org/wiki/Q6718887","display_name":"Non canonical","level":2,"score":0.1290999948978424},{"id":"https://openalex.org/C159333733","wikidata":"https://www.wikidata.org/wiki/Q7051809","display_name":"Normalization property","level":2,"score":0.12790000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.21904642","doi":"https://doi.org/10.5281/zenodo.21904642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21904642","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21904643","doi":"https://doi.org/10.5281/zenodo.21904643","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21904643","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.21904642","doi":"https://doi.org/10.5281/zenodo.21904642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21904642","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6917855220","https://openalex.org/W7215068768","https://openalex.org/W615209335","https://openalex.org/W3103959004","https://openalex.org/W7214345124","https://openalex.org/W7163999791","https://openalex.org/W2904809892","https://openalex.org/W3087696022","https://openalex.org/W7019041715","https://openalex.org/W3215934243"],"abstract_inverted_index":{"Das":[0,70,199,379],"Urheberrecht":[1],"hindert":[2],"Forscher":[3],"daran,":[4],"die":[5,27,51,59,64,179,217,254,259,264,272,354,360,403,410],"zeitgen\u00f6ssischen":[6],"Korpora,":[7],"auf":[8,102,322],"denen":[9],"ihre":[10],"Ergebnisse":[11],"beruhen,":[12],"offen":[13],"zug\u00e4nglich":[14],"zu":[15,219,227,266,269],"machen.":[16],"Abgeleitete":[17],"Textformate":[18,203],"(ATFs)":[19],"bieten":[20],"einen":[21,447],"Ausweg.":[22],"Sie":[23],"entstehen,":[24],"in":[25,34,94,126,237,280,362,425],"dem":[26],"Texte":[28],"gezielt":[29],"transformiert":[30],"werden,":[31],"und":[32,43,163,216,276,291,442],"zwar":[33],"zwei":[35,127],"Schritten:":[36],"Zun\u00e4chst":[37,326],"werden":[38,45,57,235,271,293,320,423,434],"sie":[39],"mit":[40,108,192,246,384],"Annotationen":[41,109],"angereichert":[42],"anschlie\u00dfend":[44],"so":[46],"viele":[47],"Informationen":[48,212],"entfernt,":[49],"dass":[50],"Originale":[52],"weder":[53],"gelesen":[54],"noch":[55],"rekonstruiert":[56],"k\u00f6nnen,":[58],"\u00fcbrigen":[60],"Daten":[61],"jedoch":[62],"f\u00fcr":[63,146,328,446],"computergest\u00fctzte":[65],"Analyse":[66],"weiterhin":[67],"nutzbar":[68],"bleiben.":[69],"hier":[71],"verf\u00fcgbare":[72],"ATF-Korpus":[73],"besteht":[74,169,188],"aus":[75,79,170,189,194],"15.741":[76],"deutschen":[77],"Heftromanen":[78],"den":[80,220,281,365,370,426],"Best\u00e4nden":[81],"der":[82,122,140,166,201,224,231,233,274,295,305,318,345,357,367,374,420,438],"Deutschen":[83,123,439],"Nationalbibliothek":[84,124,440],",":[85],"das":[86,253,339],"437":[87],"Millionen":[88],"Tokens":[89],"umfasst.":[90],"Jeder":[91,165],"Roman":[92],"ist":[93],"Form":[95],"von":[96],"H\u00e4ufigkeitstabellen":[97],"(Bag":[98],"of":[99,133],"Words,":[100],"BoW)":[101],"Segmentebene":[103],"(je":[104],"ca.":[105],"1.000":[106],"Tokens)":[107],"(Token,":[110],"Lemma,":[111],"Wortart,":[112],"Named":[113],"Entities)":[114],"sowie":[115],"einer":[116,261],"generierten":[117],"Zusammenfassung":[118,139],"verf\u00fcgbar.":[119],"Der":[120],"ATF-Datenbestand":[121],"wird":[125,327,382,392],"unterschiedlichen":[128],"Auspr\u00e4gungen":[129],"ATF-BoW":[130],"als":[131,138,148,177,408],"Bag":[132],"Words":[134],"(Beispiel:":[135,142],"AA_Example_ATF.tsv)":[136],"ATF-Summary":[137],"Heftromane":[141,150],"AA_Example_Summary.txt;":[143],"Prompt:":[144],"AA_Summary_Prompt.txt)":[145],"mehr":[147],"15.000":[149],"bereitgestellt.":[151,239,325],"Im":[152],"Folgenden":[153],"bezeichnet":[154],"ATF-XXX":[155],"jeweils":[156,243],"eine":[157,332,343,394],"dieser":[158],"beiden":[159,167,421],"Auspr\u00e4gungen.":[160],"Dateiformat,":[161],"Benennung":[162],"Integrit\u00e4t":[164,404,411],"Datenbest\u00e4nde":[168],"Dateien":[171,234,256,292],"im":[172,376,444],"TSV-Format.":[173],"Die":[174,186,210,289,299,418,431],"Dateinamen":[175,290,373],"enthalten":[176],"Merkmal":[178],"DNB-interne":[180],"Identifikationsnummer":[181],"(PICA":[182],"Production":[183],"Number,":[184],"PPN).":[185],"PPN":[187,215,265,279],"zehn":[190],"Zeichen":[191,193],"{0,":[195],"...,":[196],"9,":[197],"X}.":[198],"Namensschema":[200],"abgeleiteten":[202],"lautet:":[204],"<PPN>.txt.tsv":[205],"Beispiele:":[206],"1016766513.txt.tsv":[207],"101758978X.txt.tsv":[208],"102286677X.txt.tsv":[209],"weiterf\u00fchrenden":[211],"zur":[213],"jeweiligen":[214],"Zuordnung":[218,260],"bibliografischen":[221],"Metadaten":[222,427],"sind":[223],"bereitgestellten":[225],"Metadatendatei":[226],"entnehmen.":[228],"ZIP-Archive":[229],"Aufgrund":[230],"Anzahl":[232],"diese":[236],"ZIP-Archiven":[238],"Ein":[240],"Archiv":[241],"enth\u00e4lt":[242,338],"2.600":[244],"Dateien,":[245],"Ausnahme":[247],"des":[248,283,307,428],"letzten":[249,277],"Archivs":[250],"eines":[251,301,405],"Bestands,":[252],"verbleibenden":[255],"enth\u00e4lt.":[257],"Um":[258],"Datei":[262,337,375],"\u00fcber":[263],"einem":[267],"ZIP-Archiv":[268,391],"erleichtern,":[270],"Namen":[273,282],"ersten":[275],"enthaltenen":[278,414],"ZIP-Archivs":[284,302,407],"aufgenommen:":[285],"ATF-XXX-<erste-PPN>-<letzte-PPN>.zip":[286,398],"Beispiel:":[287],"ATF-Summary-132545544X-133907625X.zip":[288],"innerhalb":[294],"Archive":[296],"unver\u00e4ndert":[297],"\u00fcbernommen.":[298],"Struktur":[300,306],"entspricht":[303],"dabei":[304],"ver\u00f6ffentlichten":[308,377],"Datenbestands:":[309],"ATF-XXX/\u251c\u2500\u2500":[310],"1234567891.txt.tsv\u251c\u2500\u2500":[311],"1234567892.txt.tsv\u251c\u2500\u2500":[312],"...\u2514\u2500\u2500":[313],"123456789X.txt.tsv":[314],"Pr\u00fcfsummen":[315],"Zur":[316],"\u00dcberpr\u00fcfung":[317],"Datenintegrit\u00e4t":[319],"SHA-256-Pr\u00fcfsummen":[321,419],"mehreren":[323],"Ebenen":[324],"jede":[329,336],"einzelne":[330],"TSV-Datei":[331],"Pr\u00fcfsumme":[333,356],"berechnet.":[334],"F\u00fcr":[335,389],"zugeh\u00f6rige":[340],"Manifest":[341,380],"ATF-XXX.manifest":[342,387],"Zeile":[344],"Form:":[346],"SHA-256":[347,385],"size":[348],"iso-timestamp":[349],"filename":[350],"Dabei":[351],"bezeichnet:":[352],"SHA-256:":[353],"kryptografische":[355],"Datei,":[358,368],"size:":[359],"Dateigr\u00f6\u00dfe":[361],"Byte,":[363],"iso-timestamp:":[364],"ISO-8601-Zeitstempel":[366],"filename:":[369],"Pfad":[371],"bzw.":[372],"Bestand.":[378],"selbst":[381],"ebenfalls":[383],"abgesichert:":[386],"ATF-XXX.manifest.sha256":[388],"jedes":[390],"zus\u00e4tzlich":[393,424],"eigene":[395],"SHA-256-Pr\u00fcfsumme":[396],"bereitgestellt:":[397],"ATF-XXX-<erste-PPN>-<letzte-PPN>.zip.sha256":[399],"Damit":[400],"kann":[401],"sowohl":[402],"heruntergeladenen":[406],"auch":[409],"jeder":[412],"darin":[413],"Einzeldatei":[415],"\u00fcberpr\u00fcft":[416],"werden.":[417,451],"Gesamtmanifests":[422],"Zenodo-Records":[429],"hinterlegt.":[430],"entsprechenden":[432],"Pr\u00fcfinformationen":[433],"dar\u00fcber":[435],"hinaus":[436],"bei":[437],"vorgehalten":[441],"k\u00f6nnen":[443],"Bedarfsfall":[445],"unabh\u00e4ngigen":[448],"Abgleich":[449],"herangezogen":[450]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-08-26T00:00:00"}
