{"id":"https://openalex.org/W2533861448","doi":"https://doi.org/10.1145/2983323.2983776","title":"Scalability of Continuous Active Learning for Reliable High-Recall Text Classification","display_name":"Scalability of Continuous Active Learning for Reliable High-Recall Text Classification","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2533861448","doi":"https://doi.org/10.1145/2983323.2983776","mag":"2533861448"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983776","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983776&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2983776&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084091807","display_name":"Gordon V. Cormack","orcid":"https://orcid.org/0000-0002-5890-0293"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gordon V. Cormack","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083981495","display_name":"Maura R. Grossman","orcid":"https://orcid.org/0000-0003-2279-4262"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Maura R. Grossman","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084091807"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":11.5534,"has_fulltext":true,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98437985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1039","last_page":"1048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T11269","display_name":"Algorithms and Data Compression","score":0.9933000206947327,"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":0.9907000064849854,"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/scalability","display_name":"Scalability","score":0.787365734577179},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7132471203804016},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6781735420227051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6380971670150757},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6369529366493225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46580109000205994},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4531819820404053},{"id":"https://openalex.org/keywords/binary-logarithm","display_name":"Binary logarithm","score":0.45310068130493164},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4291735291481018},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41790467500686646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3244914412498474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2413482964038849},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.20146241784095764},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11197489500045776}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.787365734577179},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7132471203804016},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6781735420227051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6380971670150757},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6369529366493225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46580109000205994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4531819820404053},{"id":"https://openalex.org/C63553672","wikidata":"https://www.wikidata.org/wiki/Q581168","display_name":"Binary logarithm","level":2,"score":0.45310068130493164},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4291735291481018},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41790467500686646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3244914412498474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2413482964038849},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.20146241784095764},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11197489500045776},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983776","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983776&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2983323.2983776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2983323.2983776","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2983776&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2533861448.pdf","grobid_xml":"https://content.openalex.org/works/W2533861448.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W168362576","https://openalex.org/W756166754","https://openalex.org/W1554394657","https://openalex.org/W1604214695","https://openalex.org/W1643320121","https://openalex.org/W1700671489","https://openalex.org/W1993202648","https://openalex.org/W2002302568","https://openalex.org/W2027827699","https://openalex.org/W2029075138","https://openalex.org/W2037771830","https://openalex.org/W2038093061","https://openalex.org/W2040066835","https://openalex.org/W2057495142","https://openalex.org/W2065383075","https://openalex.org/W2066289596","https://openalex.org/W2074435487","https://openalex.org/W2075893676","https://openalex.org/W2085989833","https://openalex.org/W2087511931","https://openalex.org/W2118020653","https://openalex.org/W2120054496","https://openalex.org/W2120308175","https://openalex.org/W2122053905","https://openalex.org/W2124161689","https://openalex.org/W2139651995","https://openalex.org/W2142114717","https://openalex.org/W2150102617","https://openalex.org/W2165387257","https://openalex.org/W2169863116","https://openalex.org/W2341384651","https://openalex.org/W2504164904","https://openalex.org/W2521237501","https://openalex.org/W2565695915","https://openalex.org/W2573384236","https://openalex.org/W2604321711","https://openalex.org/W2903158431"],"related_works":["https://openalex.org/W2029404707","https://openalex.org/W4330338194","https://openalex.org/W4285325679","https://openalex.org/W2118758177","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W1928239295","https://openalex.org/W623261610","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"For":[0],"finite":[1],"document":[2],"collections,":[3],"continuous":[4],"active":[5],"learning":[6],"('CAL')":[7],"has":[8],"been":[9],"observed":[10],"to":[11,24,52,69],"achieve":[12],"high":[13,16],"recall":[14],"with":[15,117],"probability,":[17],"at":[18],"a":[19,79,106,111],"labeling":[20,89,113],"cost":[21,114],"asymptotically":[22],"proportional":[23,68],"the":[25,31,34,37,48,70,99,122,142,145],"number":[26,38,71,100],"of":[27,33,39,50,72,82,101,129,141,144],"relevant":[28,40,73],"documents.":[29],"As":[30],"size":[32],"collection":[35],"increases,":[36],"documents":[41,74],"typically":[42],"increases":[43],"as":[44,57],"well,":[45],"thereby":[46],"limiting":[47],"applicability":[49],"CAL":[51,83],"low-prevalence":[53],"high-stakes":[54],"classes,":[55],"such":[56],"evidence":[58],"in":[59],"legal":[60],"proceedings,":[61],"or":[62],"security":[63],"threats,":[64],"where":[65],"human":[66],"effort":[67,90],"is":[75,98],"justified.":[76],"We":[77],"present":[78],"scalable":[80],"version":[81],"('S-CAL')":[84],"that":[85],"requires":[86],"O(log":[87],"N)":[88,94],"and":[91,133,139],"O(N":[92],"log":[93],"computational":[95],"effort---where":[96],"N":[97],"unlabeled":[102],"training":[103],"examples---to":[104],"construct":[105],"classifier":[107],"whose":[108],"effectiveness":[109],"for":[110],"given":[112],"compares":[115],"favorably":[116],"previously":[118],"reported":[119],"methods.":[120],"At":[121],"same":[123],"time,":[124],"S-CAL":[125],"offers":[126],"calibrated":[127],"estimates":[128],"class":[130],"prevalence,":[131],"recall,":[132],"precision,":[134],"facilitating":[135],"both":[136],"threshold":[137],"setting":[138],"determination":[140],"adequacy":[143],"classifier.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}