{"id":"https://openalex.org/W1970948046","doi":"https://doi.org/10.1093/llc/fqt066","title":"Does size matter? Authorship attribution, small samples, big problem","display_name":"Does size matter? Authorship attribution, small samples, big problem","publication_year":2013,"publication_date":"2013-11-14","ids":{"openalex":"https://openalex.org/W1970948046","doi":"https://doi.org/10.1093/llc/fqt066","mag":"1970948046"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqt066","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqt066","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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/I172685059","display_name":"Uniwersytet Komisji Edukacji Narodowej w Krakowie","ror":"https://ror.org/030mz2444","country_code":"PL","type":"education","lineage":["https://openalex.org/I172685059"]},{"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":["Pedagogical University of Krak\u00f3w, Poland and Polish Academy of Sciences, Institute of Polish Language, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pedagogical University of Krak\u00f3w, Poland and Polish Academy of Sciences, Institute of Polish Language, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I172685059","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/I172685059","https://openalex.org/I4210107179"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":13.2567,"has_fulltext":false,"cited_by_count":203,"citation_normalized_percentile":{"value":0.98436923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"30","issue":"2","first_page":"167","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":1.0,"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":1.0,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9896000027656555,"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":0.9771999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.7850185632705688},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7512466907501221},{"id":"https://openalex.org/keywords/attributive","display_name":"Attributive","score":0.6623444557189941},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6503746509552002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5461391806602478},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.5446542501449585},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.542938768863678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5344134569168091},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5296627879142761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5099166631698608},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4668095111846924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3310849070549011},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2799869179725647},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27753210067749023},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.14152628183364868},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1223452091217041},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08824065327644348}],"concepts":[{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.7850185632705688},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7512466907501221},{"id":"https://openalex.org/C2778854177","wikidata":"https://www.wikidata.org/wiki/Q4818723","display_name":"Attributive","level":2,"score":0.6623444557189941},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6503746509552002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5461391806602478},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.5446542501449585},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.542938768863678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5344134569168091},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5296627879142761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099166631698608},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4668095111846924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3310849070549011},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2799869179725647},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27753210067749023},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14152628183364868},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1223452091217041},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08824065327644348},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqt066","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqt066","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W943947147","https://openalex.org/W1521373230","https://openalex.org/W1585563739","https://openalex.org/W1606480292","https://openalex.org/W1980872501","https://openalex.org/W1981745473","https://openalex.org/W1985988274","https://openalex.org/W1993539890","https://openalex.org/W2004340073","https://openalex.org/W2025882237","https://openalex.org/W2037643451","https://openalex.org/W2052028938","https://openalex.org/W2053967177","https://openalex.org/W2060978735","https://openalex.org/W2066216990","https://openalex.org/W2072422415","https://openalex.org/W2072828027","https://openalex.org/W2074302780","https://openalex.org/W2081514874","https://openalex.org/W2088343725","https://openalex.org/W2095069785","https://openalex.org/W2098434511","https://openalex.org/W2103909773","https://openalex.org/W2107317033","https://openalex.org/W2111802712","https://openalex.org/W2115680435","https://openalex.org/W2139593428","https://openalex.org/W2146793826","https://openalex.org/W2489357310","https://openalex.org/W2599132864","https://openalex.org/W2795674440","https://openalex.org/W4211117752","https://openalex.org/W4211134195","https://openalex.org/W4250089123","https://openalex.org/W4390804335","https://openalex.org/W6734955907"],"related_works":["https://openalex.org/W2375225369","https://openalex.org/W2296853219","https://openalex.org/W2371418444","https://openalex.org/W2804512208","https://openalex.org/W2382145876","https://openalex.org/W2868306385","https://openalex.org/W3105615387","https://openalex.org/W652148490","https://openalex.org/W2357442711","https://openalex.org/W4211265043"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,12,24,79,88,105,108,127,189],"this":[3],"study":[4],"is":[5,74],"to":[6,57,82,92,133,143,161,199],"find":[7],"such":[8],"a":[9,125,131],"minimal":[10,48,187],"size":[11],"text":[13],"samples":[14],"for":[15,31,154,193],"authorship":[16,195],"attribution":[17,196],"that":[18],"would":[19],"provide":[20],"stable":[21],"results":[22],"independent":[23],"random":[25],"noise.":[26],"A":[27],"few":[28],"controlled":[29],"tests":[30,113],"different":[32],"sample":[33,49],"lengths,":[34],"languages,":[35],"and":[36,40,69,130,137,158,169],"genres":[37],"are":[38],"discussed":[39],"compared.":[41],"Depending":[42],"on":[43],"the":[44,47,77,98,112,118,144,186],"corpus":[45],"used,":[46],"length":[50],"varied":[51],"from":[52],"2,500":[53],"words":[54,61,106],"(Latin":[55],"prose)":[56],"5,000":[58],"or":[59],"so":[60],"(in":[62],"most":[63,145,162],"cases,":[64],"including":[65],"English,":[66],"German,":[67],"Polish,":[68],"Hungarian":[70],"novels).":[71],"Another":[72],"observation":[73],"connected":[75],"with":[76],"method":[78,120],"sampling:":[80],"contrary":[81],"common":[83],"sense,":[84],"randomly":[85],"excerpted":[86],"\u2018bags":[87],"words\u2019":[89],"turned":[90,197],"out":[91,198],"be":[93,200],"much":[94],"more":[95],"effective":[96],"than":[97],"classical":[99],"solution,":[100],"i.e.":[101],"using":[102,117],"original":[103],"sequences":[104],"(\u2018passages\u2019)":[107],"desired":[109],"size.":[110],"Although":[111],"have":[114,151],"been":[115,152],"performed":[116],"Delta":[119],"(Burrows,":[121],"J.F.":[122],"(2002).":[123],"\u2018Delta\u2019:":[124],"measure":[126],"stylistic":[128],"difference":[129],"guide":[132],"likely":[134],"authorship.":[135],"Literary":[136],"Linguistic":[138],"Computing,":[139],"17(3):":[140],"267\u201387)":[141],"applied":[142,160],"frequent":[146,163],"words,":[147,164],"some":[148],"additional":[149],"experiments":[150],"conducted":[153],"support":[155],"vector":[156],"machines":[157],"k-NN":[159],"character":[165,167],"3-grams,":[166],"4-grams,":[168],"parts-of-speech-tag":[170],"3-grams.":[171],"Despite":[172],"significant":[173],"differences":[174],"in":[175],"overall":[176],"attributive":[177],"success":[178],"rate":[179],"between":[180],"particular":[181],"methods":[182],"and/or":[183],"style":[184],"markers,":[185],"amount":[188],"textual":[190],"data":[191],"needed":[192],"reliable":[194],"method-independent.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}
