{"id":"https://openalex.org/W2114634183","doi":"https://doi.org/10.1109/itcc.2004.1286699","title":"A new framework for uncertainty sampling: exploiting uncertain and positive-certain examples in similarity-based text classification","display_name":"A new framework for uncertainty sampling: exploiting uncertain and positive-certain examples in similarity-based text classification","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2114634183","doi":"https://doi.org/10.1109/itcc.2004.1286699","mag":"2114634183"},"language":"en","primary_location":{"id":"doi:10.1109/itcc.2004.1286699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itcc.2004.1286699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/A_New_Framework_for_Uncertainty_Sampling_Exploiting_Uncertain_and_Positive-Certain_Examples_in_Similarity-Based_Text_Classification/23081918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011047083","display_name":"K.H. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"K.H. Lee","raw_affiliation_strings":["School of Information Technologies, University of Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technologies, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069403329","display_name":"Byeong Ho Kang","orcid":"https://orcid.org/0000-0003-3476-8838"},"institutions":[{"id":"https://openalex.org/I129801699","display_name":"University of Tasmania","ror":"https://ror.org/01nfmeh72","country_code":"AU","type":"education","lineage":["https://openalex.org/I129801699"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"B.H. Kang","raw_affiliation_strings":["School of Computing, University of Tasmania, Hobart, TAS, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Tasmania, Hobart, TAS, Australia","institution_ids":["https://openalex.org/I129801699"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"479 Vol.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T12072","display_name":"Machine Learning and Algorithms","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/T12535","display_name":"Machine Learning and Data Classification","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/computer-science","display_name":"Computer science","score":0.721625566482544},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6528855562210083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.604322075843811},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5786418914794922},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.572561502456665},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5552444458007812},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5513906478881836},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46860894560813904},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46454739570617676},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10109630227088928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721625566482544},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6528855562210083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.604322075843811},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5786418914794922},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.572561502456665},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5552444458007812},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5513906478881836},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46860894560813904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46454739570617676},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10109630227088928},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/itcc.2004.1286699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itcc.2004.1286699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004.","raw_type":"proceedings-article"},{"id":"pmh:oai:ecite.utas.edu.au:29655","is_oa":false,"landing_page_url":"http://ecite.utas.edu.au/29655","pdf_url":null,"source":{"id":"https://openalex.org/S4306401569","display_name":"eCite Digital Repository (University of Tasmania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I129801699","host_organization_name":"University of Tasmania","host_organization_lineage":["https://openalex.org/I129801699"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Refereed Conference Paper"},{"id":"pmh:oai:figshare.com:article/23081918","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_New_Framework_for_Uncertainty_Sampling_Exploiting_Uncertain_and_Positive-Certain_Examples_in_Similarity-Based_Text_Classification/23081918","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/23081918","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_New_Framework_for_Uncertainty_Sampling_Exploiting_Uncertain_and_Positive-Certain_Examples_in_Similarity-Based_Text_Classification/23081918","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W13661906","https://openalex.org/W1513874326","https://openalex.org/W1525341925","https://openalex.org/W1979495886","https://openalex.org/W2048679005","https://openalex.org/W2063198646","https://openalex.org/W2085989833","https://openalex.org/W2094934653","https://openalex.org/W2097089247","https://openalex.org/W2098162425","https://openalex.org/W2114535528","https://openalex.org/W2136332012","https://openalex.org/W2151023586","https://openalex.org/W2164547069","https://openalex.org/W2482792214","https://openalex.org/W2895674046","https://openalex.org/W2951911250","https://openalex.org/W4230030242","https://openalex.org/W4237265687","https://openalex.org/W6631459773","https://openalex.org/W6680219600","https://openalex.org/W6684151790"],"related_works":["https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2116854923","https://openalex.org/W2750730210","https://openalex.org/W2236974868","https://openalex.org/W4312766348","https://openalex.org/W4233939244","https://openalex.org/W2730764323","https://openalex.org/W3123806511","https://openalex.org/W1976727107"],"abstract_inverted_index":{"One":[0],"of":[1,19,27,34,50,73],"the":[2,48,187],"major":[3],"concerns":[4],"with":[5,69,160],"supervised":[6],"learning":[7,137,143],"approaches":[8,45,94],"to":[9,22,46,91,106,124],"text":[10,80,97],"classification":[11,81],"is":[12],"that":[13,120,132,178],"they":[14],"require":[15],"a":[16,24,31,37,70,89,111],"large":[17,32],"number":[18,33,72],"labeled":[20,51,74],"examples":[21,35,52,59],"achieve":[23],"high":[25],"level":[26],"effectiveness.":[28],"Labeling":[29],"such":[30],"poses":[36],"considerable":[38],"burden":[39],"on":[40,84,150,169],"human":[41,125],"experts.":[42],"Two":[43],"common":[44],"reduce":[47],"amount":[49],"required":[53],"are:":[54],"(1)":[55],"selecting":[56],"informative":[57,117],"uncertain":[58,118],"for":[60,127,136],"human-labeling":[61],"and":[62,129,163,171,182],"(2)":[63],"using":[64],"many":[65],"inexpensive":[66],"unlabeled":[67],"data":[68,119,131,152],"small":[71],"examples.":[75],"While":[76],"previous":[77,164],"work":[78],"in":[79,95],"focused":[82],"only":[83],"one":[85],"approach,":[86],"we":[87,109],"investigate":[88],"framework":[90,113],"combine":[92],"both":[93,180],"similarity-based":[96,142],"classification.":[98],"By":[99],"applying":[100],"our":[101,141,192],"new":[102,112],"thresholding":[103],"strategy":[104],"(RinSCut)":[105],"uncertainty":[107],"sampling,":[108,167],"propose":[110],"which":[114],"automatically":[115],"selects":[116],"should":[121],"be":[122,191],"presented":[123],"expert":[126],"labeling":[128],"positive-certain":[130],"are":[133,185],"directly":[134],"used":[135],"without":[138],"human-labeling.":[139],"With":[140],"algorithm":[144],"(KAN),":[145],"experiments":[146],"have":[147],"been":[148,158],"conducted":[149],"Reuters-21578":[151],"set.":[153],"Our":[154],"proposed":[155],"scheme":[156],"has":[157],"compared":[159],"random":[161],"sampling":[162],"conventional":[165],"uncertainly":[166],"based":[168],"micro":[170],"macroaveraged":[172],"F/sub":[173],"1/.":[174],"The":[175],"results":[176],"showed":[177],"if":[179],"macro":[181],"microaveraged":[183],"measures":[184],"concerned,":[186],"optimal":[188],"choice":[189],"might":[190],"framework.":[193]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}