{"id":"https://openalex.org/W2602298028","doi":null,"title":"A Multitude of Linguistically-rich Features for Authorship Attribution","display_name":"A Multitude of Linguistically-rich Features for Authorship Attribution","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W2602298028","mag":"2602298028"},"language":"en","primary_location":{"id":"mag:2602298028","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00703987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HAL (Le Centre pour la Communication Scientifique Directe)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-00703987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056371786","display_name":"Ludovic Tanguy","orcid":"https://orcid.org/0009-0007-8535-8317","observed_orcids":["https://orcid.org/0009-0007-8535-8317"]},"institutions":[{"id":"https://openalex.org/I4210115900","display_name":"Laboratoire Cognition, Langues, Langage, Ergonomie","ror":"https://ror.org/029cj5595","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I159885104","https://openalex.org/I2746051580","https://openalex.org/I3130945570","https://openalex.org/I4210115900","https://openalex.org/I4210152422"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ludovic Tanguy","raw_affiliation_strings":["Cognition, Langues, Langage, Ergonomie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognition, Langues, Langage, Ergonomie","institution_ids":["https://openalex.org/I4210115900"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082126682","display_name":"Assaf Urieli","orcid":"https://orcid.org/0009-0000-0929-4699","observed_orcids":["https://orcid.org/0009-0000-0929-4699"]},"institutions":[{"id":"https://openalex.org/I4210115900","display_name":"Laboratoire Cognition, Langues, Langage, Ergonomie","ror":"https://ror.org/029cj5595","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I159885104","https://openalex.org/I2746051580","https://openalex.org/I3130945570","https://openalex.org/I4210115900","https://openalex.org/I4210152422"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Assaf Urieli","raw_affiliation_strings":["Cognition, Langues, Langage, Ergonomie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognition, Langues, Langage, Ergonomie","institution_ids":["https://openalex.org/I4210115900"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110738144","display_name":"Basilio Calderone","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210115900","display_name":"Laboratoire Cognition, Langues, Langage, Ergonomie","ror":"https://ror.org/029cj5595","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I159885104","https://openalex.org/I2746051580","https://openalex.org/I3130945570","https://openalex.org/I4210115900","https://openalex.org/I4210152422"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Basilio Calderone","raw_affiliation_strings":["Cognition, Langues, Langage, Ergonomie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognition, Langues, Langage, Ergonomie","institution_ids":["https://openalex.org/I4210115900"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071878312","display_name":"Nabil Hathout","orcid":"https://orcid.org/0000-0003-4492-171X","observed_orcids":["https://orcid.org/0000-0003-4492-171X"]},"institutions":[{"id":"https://openalex.org/I4210115900","display_name":"Laboratoire Cognition, Langues, Langage, Ergonomie","ror":"https://ror.org/029cj5595","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I159885104","https://openalex.org/I2746051580","https://openalex.org/I3130945570","https://openalex.org/I4210115900","https://openalex.org/I4210152422"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nabil Hathout","raw_affiliation_strings":["Cognition, Langues, Langage, Ergonomie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognition, Langues, Langage, Ergonomie","institution_ids":["https://openalex.org/I4210115900"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036280668","display_name":"Franck Sajous","orcid":"https://orcid.org/0000-0001-9439-3658","observed_orcids":["https://orcid.org/0000-0001-9439-3658"]},"institutions":[{"id":"https://openalex.org/I4210115900","display_name":"Laboratoire Cognition, Langues, Langage, Ergonomie","ror":"https://ror.org/029cj5595","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I159885104","https://openalex.org/I2746051580","https://openalex.org/I3130945570","https://openalex.org/I4210115900","https://openalex.org/I4210152422"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Sajous","raw_affiliation_strings":["Cognition, Langues, Langage, Ergonomie"],"raw_orcid":"https://orcid.org/0000-0001-9439-3658","affiliations":[{"raw_affiliation_string":"Cognition, Langues, Langage, Ergonomie","institution_ids":["https://openalex.org/I4210115900"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210115900"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"-","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9994999766349792,"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":0.9994999766349792,"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/T11800","display_name":"User Authentication and Security Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/authorship-attribution","display_name":"authorship attribution","score":0.9470000267028809},{"id":"https://openalex.org/keywords/linguistic-features","display_name":"linguistic features","score":0.8460000157356262},{"id":"https://openalex.org/keywords/maximum-entropy-model","display_name":"maximum entropy model","score":0.7009999752044678},{"id":"https://openalex.org/keywords/symbolic-learning","display_name":"symbolic learning","score":0.6449999809265137},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.871999979019165},{"id":"https://openalex.org/keywords/email-corpus","display_name":"email corpus","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952636480331421},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7880001664161682},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.6775217056274414},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6683632135391235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009755730628967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5940081477165222},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.527711808681488},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48443081974983215},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.47296327352523804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44097137451171875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3387168049812317},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2602298028","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00703987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HAL (Le Centre pour la Communication Scientifique Directe)","raw_type":null},{"id":"pmh:oai:HAL:hal-00703987v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00703987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PAN Lab at CLEF, Sep 2011, Amsterdam, Netherlands","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"mag:2602298028","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00703987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HAL (Le Centre pour la Communication Scientifique Directe)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W31924142","https://openalex.org/W141948786","https://openalex.org/W146156986","https://openalex.org/W1504694836","https://openalex.org/W1533946607","https://openalex.org/W1585743408","https://openalex.org/W1670263352","https://openalex.org/W2013568550","https://openalex.org/W2038721957","https://openalex.org/W2043976122","https://openalex.org/W2072828027","https://openalex.org/W2074118501","https://openalex.org/W2096765155","https://openalex.org/W2097606805","https://openalex.org/W2125055259","https://openalex.org/W2128870637","https://openalex.org/W2133990480","https://openalex.org/W2158873310","https://openalex.org/W2613904154","https://openalex.org/W2912780347"],"related_works":["https://openalex.org/W2405646588","https://openalex.org/W2187195488","https://openalex.org/W2069115618","https://openalex.org/W7099660880","https://openalex.org/W2401936037","https://openalex.org/W2407639214","https://openalex.org/W1560637250","https://openalex.org/W7100720926","https://openalex.org/W7098859837","https://openalex.org/W3042582162"],"abstract_inverted_index":{"This":[0,112],"paper":[1,113],"reports":[2],"on":[3,88],"the":[4,12,36,56,77,89,93,117,121,123,127],"procedure":[5],"and":[6,39,105,108,126],"learning":[7,102,124],"models":[8,125],"we":[9],"adopted":[10],"for":[11,100],"'PAN":[13],"2011":[14],"Author":[15],"Identification'":[16],"challenge":[17],"targetting":[18],"real-world":[19],"email":[20],"messages.":[21],"The":[22],"novelty":[23],"of":[24,35,46,84,92],"our":[25],"approach":[26],"lies":[27],"in":[28,115],"a":[29,43,67,82],"design":[30],"which":[31,71],"combines":[32],"shallow":[33],"characteristics":[34],"emails":[37],"(words":[38],"trigrams":[40],"frequencies)":[41],"with":[42],"large":[44],"number":[45],"ad":[47],"hoc":[48],"linguistically-rich":[49],"features":[50,62,85,118],"addressing":[51],"different":[52],"language":[53],"levels.":[54],"For":[55,76],"author":[57,79],"attribution":[58],"tasks,":[59,81],"all":[60],"these":[61],"were":[63],"used":[64],"to":[65],"train":[66],"maximum":[68],"entropy":[69],"model":[70],"gave":[72,109],"very":[73],"good":[74],"results.":[75,111],"single":[78],"verification":[80],"set":[83],"exclusively":[86],"based":[87],"linguistic":[90],"description":[91],"emails'":[94],"messages":[95],"was":[96],"considered":[97],"as":[98],"input":[99],"symbolic":[101],"techniques":[103],"(rules":[104],"decision":[106],"trees),":[107],"weak":[110],"presents":[114],"detail":[116],"extracted":[119],"from":[120],"corpus,":[122],"results":[128],"obtained.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2017-04-07T00:00:00"}