{"id":"https://openalex.org/W4414847839","doi":"https://doi.org/10.3390/e27101039","title":"The Amount of Data Required to Recognize a Writer\u2019s Style Is Consistent Across Different Languages of the World","display_name":"The Amount of Data Required to Recognize a Writer\u2019s Style Is Consistent Across Different Languages of the World","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4414847839","doi":"https://doi.org/10.3390/e27101039","pmid":"https://pubmed.ncbi.nlm.nih.gov/41148997"},"language":"en","primary_location":{"id":"doi:10.3390/e27101039","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27101039","pdf_url":"https://www.mdpi.com/1099-4300/27/10/1039/pdf?version=1759582319","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/27/10/1039/pdf?version=1759582319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028123461","display_name":"Boris Ryabko","orcid":"https://orcid.org/0000-0002-7232-9644"},"institutions":[{"id":"https://openalex.org/I188973947","display_name":"Novosibirsk State University","ror":"https://ror.org/04t2ss102","country_code":"RU","type":"education","lineage":["https://openalex.org/I188973947"]},{"id":"https://openalex.org/I4210137651","display_name":"Federal Research Center for Information and Computational Technologies","ror":"https://ror.org/02x3mf211","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210137651"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Boris Ryabko","raw_affiliation_strings":["Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia","Federal Research Center for Information and Computational Technologies, 6300090 Novosibirsk, Russia"],"raw_orcid":"https://orcid.org/0000-0002-7232-9644","affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia","institution_ids":["https://openalex.org/I188973947"]},{"raw_affiliation_string":"Federal Research Center for Information and Computational Technologies, 6300090 Novosibirsk, Russia","institution_ids":["https://openalex.org/I4210137651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078460503","display_name":"Nadezhda Savina","orcid":"https://orcid.org/0000-0001-9765-9714"},"institutions":[{"id":"https://openalex.org/I188973947","display_name":"Novosibirsk State University","ror":"https://ror.org/04t2ss102","country_code":"RU","type":"education","lineage":["https://openalex.org/I188973947"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nadezhda Savina","raw_affiliation_strings":["Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia"],"raw_orcid":"https://orcid.org/0000-0001-9765-9714","affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia","institution_ids":["https://openalex.org/I188973947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093461495","display_name":"Yeshewas Getachew Lulu","orcid":"https://orcid.org/0009-0006-8054-9846"},"institutions":[{"id":"https://openalex.org/I188973947","display_name":"Novosibirsk State University","ror":"https://ror.org/04t2ss102","country_code":"RU","type":"education","lineage":["https://openalex.org/I188973947"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yeshewas Getachew Lulu","raw_affiliation_strings":["Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia"],"raw_orcid":"https://orcid.org/0009-0006-8054-9846","affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia","institution_ids":["https://openalex.org/I188973947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102954169","display_name":"Yunfei Han","orcid":"https://orcid.org/0000-0001-7455-9008"},"institutions":[{"id":"https://openalex.org/I188973947","display_name":"Novosibirsk State University","ror":"https://ror.org/04t2ss102","country_code":"RU","type":"education","lineage":["https://openalex.org/I188973947"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yunfei Han","raw_affiliation_strings":["Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Novosibirsk State University, 6300090 Novosibirsk, Russia","institution_ids":["https://openalex.org/I188973947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028123461"],"corresponding_institution_ids":["https://openalex.org/I188973947","https://openalex.org/I4210137651"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13203192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"10","first_page":"1039","last_page":"1039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.8051999807357788,"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":0.8051999807357788,"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/T12970","display_name":"Names, Identity, and Discrimination Research","score":0.708299994468689,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T10759","display_name":"Translation Studies and Practices","score":0.6736000180244446,"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/amharic","display_name":"Amharic","score":0.6244999766349792},{"id":"https://openalex.org/keywords/semitic-languages","display_name":"Semitic languages","score":0.597100019454956},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5720999836921692},{"id":"https://openalex.org/keywords/slavic-languages","display_name":"Slavic languages","score":0.4722999930381775},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44269999861717224},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.3937999904155731},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.37940001487731934},{"id":"https://openalex.org/keywords/object-language","display_name":"Object language","score":0.34290000796318054}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6940000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638000011444092},{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.6244999766349792},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.597100019454956},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C121894898","wikidata":"https://www.wikidata.org/wiki/Q23526","display_name":"Slavic languages","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4681999981403351},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C185954173","wikidata":"https://www.wikidata.org/wiki/Q4347052","display_name":"Object language","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C24570573","wikidata":"https://www.wikidata.org/wiki/Q7191197","display_name":"Picture language","level":5,"score":0.33309999108314514},{"id":"https://openalex.org/C116081451","wikidata":"https://www.wikidata.org/wiki/Q1501364","display_name":"Language transfer","level":4,"score":0.2964000105857849},{"id":"https://openalex.org/C114010052","wikidata":"https://www.wikidata.org/wiki/Q150352","display_name":"Foreign language","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C550607084","wikidata":"https://www.wikidata.org/wiki/Q1410327","display_name":"Language contact","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C159403335","wikidata":"https://www.wikidata.org/wiki/Q207857","display_name":"Inflection","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C48580701","wikidata":"https://www.wikidata.org/wiki/Q150","display_name":"French","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C524601802","wikidata":"https://www.wikidata.org/wiki/Q2198157","display_name":"Quantitative linguistics","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/e27101039","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27101039","pdf_url":"https://www.mdpi.com/1099-4300/27/10/1039/pdf?version=1759582319","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:41148997","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41148997","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:dd613fc7070e4dce92707c5c34286a47","is_oa":true,"landing_page_url":"https://doaj.org/article/dd613fc7070e4dce92707c5c34286a47","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 27, Iss 10, p 1039 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11366036","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12563418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e27101039","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27101039","pdf_url":"https://www.mdpi.com/1099-4300/27/10/1039/pdf?version=1759582319","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414847839.pdf","grobid_xml":"https://content.openalex.org/works/W4414847839.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,42],"this":[1,43],"paper,":[2,44],"we":[3],"apply":[4],"an":[5,105],"information-theoretic":[6],"method":[7,47],"proposed":[8],"by":[9],"Ryabko":[10],"and":[11,40,83],"Savina":[12],"(therefore":[13],"called":[14],"the":[15,19,26,45,62,71,79,90,98,110,117],"RS-method),":[16],"based":[17],"on":[18],"use":[20],"of":[21,30,59,61,70,78,89,100,119,131],"data":[22,101,120],"compression,":[23],"to":[24,50,133],"recognize":[25],"individual":[27],"author's":[28,106],"style":[29,107],"a":[31],"writer":[32],"across":[33,123],"four":[34,114],"languages":[35,60],"from":[36],"different":[37,124],"language":[38,64,73,81,87,92,125],"groups":[39],"families.":[41],"presented":[46],"was":[48,95],"used":[49],"study":[51],"fiction":[52],"texts":[53],"in":[54,140],"Russian":[55],"(East":[56],"Slavic":[57],"group":[58,69,77,88],"Indo-European":[63,91],"family),":[65,74],"Amharic":[66],"(South":[67],"Ethiosemitic":[68],"Semitic":[72],"Chinese":[75],"(Sinitic":[76],"Sino-Tibetan":[80],"family)":[82],"English":[84],"(West":[85],"Germanic":[86],"family).":[93],"It":[94],"found":[96],"that":[97],"amount":[99,118],"necessary":[102],"for":[103,112],"recognizing":[104],"is":[108,121],"almost":[109],"same":[111],"all":[113],"languages,":[115],"i.e.,":[116],"invariant":[122],"groups.":[126],"The":[127],"results":[128],"obtained":[129],"are":[130],"interest":[132],"computer":[134],"science,":[135],"literary":[136],"studies,":[137],"linguistics":[138],"and,":[139],"particular,":[141],"computational":[142],"linguistics.":[143]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
