{"id":"https://openalex.org/W4200332258","doi":"https://doi.org/10.3233/jifs-219226","title":"Unsupervised authorship attribution using feature selection and weighted cosine similarity","display_name":"Unsupervised authorship attribution using feature selection and weighted cosine similarity","publication_year":2021,"publication_date":"2021-12-19","ids":{"openalex":"https://openalex.org/W4200332258","doi":"https://doi.org/10.3233/jifs-219226"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-219226","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-219226","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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/A5012975951","display_name":"Carolina Mart\u00edn-del-Campo-Rodr\u00edguez","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Carolina Mart\u00edn-del-Campo-Rodr\u00edguez","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Grigori Sidorov","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010915932","display_name":"Ildar Batyrshin","orcid":"https://orcid.org/0000-0003-0241-7902"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ildar Batyrshin","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional, Centro de Investigaci\u00f3n en Computaci\u00f3n, Av. Juan de Dios B\u00e1tiz, s/n, Col. Nueva Industrial Vallejo, Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008287867"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64966114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"42","issue":"5","first_page":"4357","last_page":"4367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.982200026512146,"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/T10028","display_name":"Topic Modeling","score":0.9815000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.8170446157455444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345381379127502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7018834948539734},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6297779083251953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6107398271560669},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6079882383346558},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.5398868918418884},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5252582430839539},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.49310681223869324},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4905923902988434},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4789341390132904},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4694998264312744},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.44962507486343384},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4449444115161896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4211823344230652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3577989339828491},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31154489517211914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1838771104812622},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06824427843093872}],"concepts":[{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.8170446157455444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345381379127502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7018834948539734},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6297779083251953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6107398271560669},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6079882383346558},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.5398868918418884},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5252582430839539},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.49310681223869324},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4905923902988434},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4789341390132904},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4694998264312744},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.44962507486343384},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4449444115161896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4211823344230652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3577989339828491},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31154489517211914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1838771104812622},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06824427843093872},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-219226","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-219226","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W176237927","https://openalex.org/W1980688822","https://openalex.org/W2072240081","https://openalex.org/W2101234009","https://openalex.org/W2153233077","https://openalex.org/W2262981901","https://openalex.org/W2295585256","https://openalex.org/W2753434909","https://openalex.org/W2895799718","https://openalex.org/W2907753072","https://openalex.org/W2935358086","https://openalex.org/W2946479819","https://openalex.org/W4230823111","https://openalex.org/W4250089123","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W4248020907","https://openalex.org/W57923944","https://openalex.org/W1992371859","https://openalex.org/W2284045667","https://openalex.org/W2970261771","https://openalex.org/W1823511492","https://openalex.org/W2518415416","https://openalex.org/W1538862850","https://openalex.org/W4237625828","https://openalex.org/W4200332258"],"abstract_inverted_index":{"This":[0,113],"paper":[1],"presents":[2],"a":[3,14,55],"computational":[4],"model":[5],"for":[6],"the":[7,22,25,36,77,82,100,106,127],"unsupervised":[8],"authorship":[9,132],"attribution":[10],"task":[11],"based":[12],"on":[13,35],"traditional":[15],"machine":[16],"learning":[17],"scheme.":[18],"An":[19],"improvement":[20],"over":[21],"state":[23],"of":[24,76],"art":[26],"is":[27,96,115],"achieved":[28],"by":[29,60,104,126],"comparing":[30],"different":[31],"feature":[32],"selection":[33],"methods":[34,50],"PAN17":[37],"author":[38],"clustering":[39,128],"dataset.":[40],"To":[41],"achieve":[42],"this":[43],"improvement,":[44],"specific":[45],"pre-processing":[46],"and":[47],"features":[48],"extraction":[49],"were":[51],"proposed,":[52],"such":[53],"as":[54,74],"method":[56],"to":[57,62,65,80,98,117,130],"separate":[58],"tokens":[59],"type":[61],"assign":[63],"them":[64],"only":[66],"one":[67],"category.":[68],"Similarly,":[69],"special":[70],"characters":[71],"are":[72,111,124],"used":[73,116],"part":[75],"punctuation":[78],"marks":[79],"improve":[81,99],"result":[83],"obtained":[84],"when":[85],"applying":[86],"typed":[87],"character":[88],"n":[89],"-grams.":[90],"The":[91],"Weighted":[92],"cosine":[93],"similarity":[94],"measure":[95,114],"applied":[97],"B":[101],"3":[102],"F-score":[103],"reducing":[105],"vector":[107],"values":[108],"where":[109],"attributes":[110],"exclusive.":[112],"define":[118],"distances":[119],"between":[120],"documents,":[121],"which":[122],"later":[123],"occupied":[125],"algorithm":[129],"perform":[131],"attribution.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2025-10-10T00:00:00"}