{"id":"https://openalex.org/W4281726995","doi":"https://doi.org/10.1080/09296174.2022.2122751","title":"Stylistic Fingerprints, POS-tags, and Inflected Languages: A Case Study in Polish","display_name":"Stylistic Fingerprints, POS-tags, and Inflected Languages: A Case Study in Polish","publication_year":2022,"publication_date":"2022-09-18","ids":{"openalex":"https://openalex.org/W4281726995","doi":"https://doi.org/10.1080/09296174.2022.2122751"},"language":"en","primary_location":{"id":"doi:10.1080/09296174.2022.2122751","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296174.2022.2122751","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847","https://openalex.org/P4310320547"],"host_organization_lineage_names":["Routledge","Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2206.02208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052407843","display_name":"Maciej Eder","orcid":"https://orcid.org/0000-0002-1429-5036"},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Maciej Eder","raw_affiliation_strings":["Polish Academy od Sciences: Instytut Jezyka Polskiego Polskiej Akademii Nauk"],"raw_orcid":"https://orcid.org/0000-0002-1429-5036","affiliations":[{"raw_affiliation_string":"Polish Academy od Sciences: Instytut Jezyka Polskiego Polskiej Akademii Nauk","institution_ids":["https://openalex.org/I4210107179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056507134","display_name":"Rafa\u0142. L. G\u00f3rski","orcid":null},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 L. G\u00f3rski","raw_affiliation_strings":["Jagiellonian University","Polish Academy od Sciences: Instytut Jezyka Polskiego Polskiej Akademii Nauk"],"raw_orcid":"https://orcid.org/0000-0003-4727-2639","affiliations":[{"raw_affiliation_string":"Jagiellonian University","institution_ids":["https://openalex.org/I126596746"]},{"raw_affiliation_string":"Polish Academy od Sciences: Instytut Jezyka Polskiego Polskiej Akademii Nauk","institution_ids":["https://openalex.org/I4210107179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052407843"],"corresponding_institution_ids":["https://openalex.org/I4210107179"],"apc_list":null,"apc_paid":null,"fwci":0.1161,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50853613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":"1","first_page":"86","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9972000122070312,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9972000122070312,"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/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9523000121116638,"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/computer-science","display_name":"Computer science","score":0.7777796983718872},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7631908655166626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7317614555358887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6627868413925171},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.6547917127609253},{"id":"https://openalex.org/keywords/lexis","display_name":"Lexis","score":0.6045291423797607},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5261399745941162},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.494312047958374},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.43250924348831177},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.42865586280822754},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.42148834466934204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777796983718872},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7631908655166626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7317614555358887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6627868413925171},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.6547917127609253},{"id":"https://openalex.org/C516687495","wikidata":"https://www.wikidata.org/wiki/Q3226977","display_name":"Lexis","level":2,"score":0.6045291423797607},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5261399745941162},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.494312047958374},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.43250924348831177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42865586280822754},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.42148834466934204},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/09296174.2022.2122751","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296174.2022.2122751","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847","https://openalex.org/P4310320547"],"host_organization_lineage_names":["Routledge","Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"},{"id":"doi:10.48550/arxiv.2206.02208","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.02208","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2206.02208","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.02208","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1843515729","https://openalex.org/W2004340073","https://openalex.org/W2009312480","https://openalex.org/W2025882237","https://openalex.org/W2095069785","https://openalex.org/W2098434511","https://openalex.org/W2107317033","https://openalex.org/W2131406793","https://openalex.org/W2146793826","https://openalex.org/W2170505850","https://openalex.org/W2173160936","https://openalex.org/W2251049886","https://openalex.org/W2765151303","https://openalex.org/W2787026234","https://openalex.org/W4211134195","https://openalex.org/W4250089123"],"related_works":["https://openalex.org/W12967685","https://openalex.org/W6643695","https://openalex.org/W10132401","https://openalex.org/W2864082","https://openalex.org/W5516682","https://openalex.org/W11449207","https://openalex.org/W6748678","https://openalex.org/W11095331","https://openalex.org/W4098470","https://openalex.org/W3030169"],"abstract_inverted_index":{"In":[0,24],"stylometric":[1],"investigations,":[2],"frequencies":[3,50],"of":[4,60,73,77,85,107,110,112,121,128,143,152,164],"the":[5,61,71,83,104,108,137,150,167],"most":[6,53],"frequent":[7],"words":[8],"(MFWs)":[9],"and":[10,33,93,116,145,172],"character":[11],"n-grams":[12],"outperform":[13],"other":[14],"style-markers,":[15],"even":[16],"if":[17,149],"their":[18],"performance":[19,72,151],"varies":[20],"significantly":[21],"across":[22],"languages.":[23],"inflected":[25,46],"languages,":[26],"word":[27,36,47],"endings":[28],"play":[29],"a":[30,119,126],"prominent":[31],"role,":[32],"hence":[34],"different":[35,141],"forms":[37,48,95,158],"cannot":[38],"be":[39],"recognized":[40],"using":[41],"generic":[42],"text":[43],"tokenization.":[44],"Countless":[45],"make":[49],"sparse,":[51],"making":[52],"statistical":[54],"procedures":[55],"complicated.":[56],"Presumably,":[57],"applying":[58],"one":[59],"NLP":[62],"techniques,":[63],"such":[64],"as":[65,154,156],"lemmatization":[66],"and/or":[67],"parsing,":[68],"might":[69],"increase":[70],"classification.":[74],"The":[75],"aim":[76],"this":[78],"paper":[79],"is":[80],"to":[81,102,135],"examine":[82],"usefulness":[84],"grammatical":[86],"features":[87],"(as":[88],"assessed":[89],"via":[90],"POS-tag":[91],"n-grams)":[92],"lemmatized":[94,157],"in":[96,100,133],"recognizing":[97],"authorial":[98],"profiles,":[99],"order":[101,134],"address":[103],"underlying":[105],"issue":[106],"degree":[109],"freedom":[111],"choice":[113],"within":[114],"lexis":[115],"grammar.":[117],"Using":[118],"corpus":[120],"Polish":[122],"novels,":[123],"we":[124],"performed":[125],"series":[127],"supervised":[129],"authorship":[130],"attribution":[131],"benchmarks,":[132],"compare":[136],"classification":[138],"accuracy":[139],"for":[140],"types":[142],"lexical":[144,165],"syntactic":[146],"style-markers.":[147],"Even":[148],"POS-tags":[153],"well":[155],"was":[159,169],"notoriously":[160],"worse":[161],"than":[162],"that":[163],"markers,":[166],"difference":[168],"not":[170],"substantial":[171],"never":[173],"exceeded":[174],"ca.":[175],"15%.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2022-06-13T00:00:00"}
