{"id":"https://openalex.org/W4404132392","doi":"https://doi.org/10.1162/tacl_a_00709","title":"Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification","display_name":"Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404132392","doi":"https://doi.org/10.1162/tacl_a_00709"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00709","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00709","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://dx.doi.org/10.1162/tacl_a_00709","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092596412","display_name":"Jitkapat Sawatphol","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153049","display_name":"Vidyasirimedhi Institute of Science and Technology","ror":"https://ror.org/053jehz60","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210153049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Jitkapat Sawatphol","raw_affiliation_strings":["School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. jitkapat.s_s20@vistec.ac.th"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. jitkapat.s_s20@vistec.ac.th","institution_ids":["https://openalex.org/I4210153049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072133587","display_name":"Can Udomcharoenchaikit","orcid":"https://orcid.org/0000-0002-7090-0536"},"institutions":[{"id":"https://openalex.org/I4210153049","display_name":"Vidyasirimedhi Institute of Science and Technology","ror":"https://ror.org/053jehz60","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210153049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Can Udomcharoenchaikit","raw_affiliation_strings":["School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. canu_pro@vistec.ac.th"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. canu_pro@vistec.ac.th","institution_ids":["https://openalex.org/I4210153049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071030042","display_name":"Sarana Nutanong","orcid":"https://orcid.org/0000-0003-1068-850X"},"institutions":[{"id":"https://openalex.org/I4210153049","display_name":"Vidyasirimedhi Institute of Science and Technology","ror":"https://ror.org/053jehz60","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210153049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sarana Nutanong","raw_affiliation_strings":["School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. snutanon@vistec.ac.th"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology, Thailand. snutanon@vistec.ac.th","institution_ids":["https://openalex.org/I4210153049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153049"],"apc_list":null,"apc_paid":null,"fwci":0.2374,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65401798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1363","last_page":"1377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8143041729927063},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.5509119629859924},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40730440616607666},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.403202623128891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143041729927063},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5509119629859924},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40730440616607666},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.403202623128891},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl_a_00709","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00709","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00709","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00709","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1490796714","https://openalex.org/W1607035479","https://openalex.org/W2101234009","https://openalex.org/W2613995098","https://openalex.org/W2740642134","https://openalex.org/W2895715183","https://openalex.org/W2946034758","https://openalex.org/W2955901475","https://openalex.org/W2970019270","https://openalex.org/W2970641574","https://openalex.org/W3034831508","https://openalex.org/W3100895823","https://openalex.org/W3191640844","https://openalex.org/W3214222557","https://openalex.org/W4205619213","https://openalex.org/W4223992738","https://openalex.org/W4231510805","https://openalex.org/W4385572919","https://openalex.org/W4385573206","https://openalex.org/W4392669807","https://openalex.org/W6604020053","https://openalex.org/W6639619044","https://openalex.org/W6675354045","https://openalex.org/W6686712581","https://openalex.org/W6691776950","https://openalex.org/W6739651123","https://openalex.org/W6755207826","https://openalex.org/W6765473094","https://openalex.org/W6785295733"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"Authorship":[1,134],"verification":[2],"(AV)":[3],"aims":[4],"to":[5,143],"identify":[6],"whether":[7],"a":[8,75,79,92],"pair":[9],"of":[10,20,96,110,114,120,127],"texts":[11],"has":[12],"the":[13,18,121,125],"same":[14],"author.":[15],"We":[16],"address":[17,61],"challenge":[19],"evaluating":[21],"AV":[22,145],"models\u2019":[23,146],"robustness":[24],"against":[25],"topic":[26,33,48,82,115,128,140],"shifts.":[27],"The":[28,132],"conventional":[29],"evaluation":[30,66,102],"assumes":[31],"minimal":[32],"overlap":[34],"between":[35],"training":[36],"and":[37,57,101,112,130],"test":[38,51,142],"data.":[39],"However,":[40],"we":[41,63],"argue":[42],"that":[43,88,138],"there":[44],"can":[45],"still":[46],"be":[47],"leakage":[49],"in":[50,123],"data,":[52],"causing":[53],"misleading":[54],"model":[55],"performance":[56],"unstable":[58],"rankings.":[59],"To":[60],"this,":[62],"propose":[64],"an":[65],"method":[67],"called":[68],"Heterogeneity-Informed":[69],"Topic":[70],"Sampling":[71],"(HITS),":[72],"which":[73],"creates":[74],"smaller":[76],"dataset":[77],"with":[78],"heterogeneously":[80],"distributed":[81],"set.":[83],"Our":[84,104],"experimental":[85],"results":[86],"demonstrate":[87],"HITS-sampled":[89],"datasets":[90],"yield":[91],"more":[93],"stable":[94],"ranking":[95],"models":[97],"across":[98],"random":[99],"seeds":[100],"splits.":[103],"contributions":[105],"include:":[106],"1.":[107],"An":[108],"analysis":[109],"causes":[111],"effects":[113,126],"leakage;":[116,129],"2.":[117],"A":[118],"demonstration":[119],"HITS":[122],"reducing":[124],"3.":[131],"Robust":[133],"Verification":[135],"bENchmark":[136],"(RAVEN)":[137],"allows":[139],"shortcut":[141],"uncover":[144],"reliance":[147],"on":[148],"topic-specific":[149],"features.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}
