{"id":"https://openalex.org/W2074435487","doi":"https://doi.org/10.1145/2484028.2484159","title":"Sequential testing in classifier evaluation yields biased estimates of effectiveness","display_name":"Sequential testing in classifier evaluation yields biased estimates of effectiveness","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2074435487","doi":"https://doi.org/10.1145/2484028.2484159","mag":"2074435487"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-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/A5110722281","display_name":"William Webber","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Webber","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010624110","display_name":"Mossaab Bagdouri","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mossaab Bagdouri","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020081385","display_name":"David Lewis","orcid":"https://orcid.org/0000-0002-3503-4644"},"institutions":[{"id":"https://openalex.org/I4210148173","display_name":"Morgan, Lewis & Bockius (United States)","ror":"https://ror.org/04c0z3e83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David D. Lewis","raw_affiliation_strings":["David D. Lewis Consulting, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"David D. Lewis Consulting, Chicago, IL, USA","institution_ids":["https://openalex.org/I4210148173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074322406","display_name":"Douglas W. Oard","orcid":"https://orcid.org/0000-0002-1696-0407"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas W. Oard","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110722281"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":1.4428,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85954853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"933","last_page":"936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.998199999332428,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.998199999332428,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980000257492065,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9973999857902527,"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/classifier","display_name":"Classifier (UML)","score":0.7108639478683472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967101097106934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5760713219642639},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5474089980125427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5362327098846436},{"id":"https://openalex.org/keywords/sequential-analysis","display_name":"Sequential analysis","score":0.4542745053768158},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4306093454360962},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.4163903295993805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3576814532279968},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.30471551418304443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1693086326122284}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7108639478683472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967101097106934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5760713219642639},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5474089980125427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362327098846436},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.4542745053768158},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4306093454360962},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4163903295993805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3576814532279968},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30471551418304443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1693086326122284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484028.2484159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1584308190","https://openalex.org/W1989584148","https://openalex.org/W2035720976","https://openalex.org/W2038390905","https://openalex.org/W2066289596","https://openalex.org/W2091082553","https://openalex.org/W2138263042","https://openalex.org/W2150102617","https://openalex.org/W2153962014","https://openalex.org/W4253803546","https://openalex.org/W4256232412","https://openalex.org/W4301209444"],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292","https://openalex.org/W2165396616","https://openalex.org/W2058882606"],"abstract_inverted_index":{"It":[0],"is":[1],"common":[2],"to":[3,33,56,65,80],"develop":[4],"and":[5,72],"validate":[6],"classifiers":[7],"through":[8],"a":[9,41],"process":[10],"of":[11,20,36,43,59],"repeated":[12,30],"testing,":[13],"with":[14],"nested":[15],"training":[16],"and/or":[17],"test":[18],"sets":[19],"increasing":[21],"size.":[22],"We":[23,61],"demonstrate":[24],"in":[25],"this":[26],"paper":[27],"that":[28,77],"such":[29],"testing":[31,50],"leads":[32],"biased":[34],"estimates":[35,58,67],"classifier":[37],"effectiveness.":[38,60],"Experiments":[39],"on":[40,68],"range":[42],"text":[44],"classification":[45],"tasks":[46],"under":[47],"three":[48,54],"sequential":[49],"frameworks":[51],"show":[52],"all":[53],"lead":[55,79],"optimistic":[57],"calculate":[62],"empirical":[63],"adjustments":[64],"unbias":[66],"our":[69],"data":[70],"set,":[71],"identify":[73],"directions":[74],"for":[75,83],"research":[76],"could":[78],"general":[81],"techniques":[82],"avoiding":[84],"bias":[85],"while":[86],"reducing":[87],"labeling":[88],"costs.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}