{"id":"https://openalex.org/W2098736260","doi":"https://doi.org/10.1109/icdm.2003.1250959","title":"Mining relevant text from unlabelled documents","display_name":"Mining relevant text from unlabelled documents","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2098736260","doi":"https://doi.org/10.1109/icdm.2003.1250959","mag":"2098736260"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","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/A5089029917","display_name":"Daniel Barbar\u00e1","orcid":"https://orcid.org/0000-0002-2830-1038"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Barbara","raw_affiliation_strings":["Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090148962","display_name":"Carlotta Domeniconi","orcid":"https://orcid.org/0000-0003-2140-9596"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Domeniconi","raw_affiliation_strings":["Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076346443","display_name":"Kang Ning","orcid":"https://orcid.org/0000-0003-3325-5387"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Kang","raw_affiliation_strings":["Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Software Engineering Department, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"[Information and Software Engineering Department, George Mason University, Fairfax, VA, USA]","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76107564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"489","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.995199978351593,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9943000078201294,"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":0.8132091760635376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7072519063949585},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6470286846160889},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6445369720458984},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6039407253265381},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5954174399375916},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5229378938674927},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43184226751327515},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.4275822639465332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3311005234718323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132091760635376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7072519063949585},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6470286846160889},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6445369720458984},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6039407253265381},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5954174399375916},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5229378938674927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43184226751327515},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.4275822639465332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3311005234718323},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2003.1250959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.1958","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.1958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ise.gmu.edu/~carlotta/publications/icdm03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W1493036841","https://openalex.org/W1546703457","https://openalex.org/W1564518192","https://openalex.org/W2048679005","https://openalex.org/W2098162425","https://openalex.org/W2104052971","https://openalex.org/W2133604244","https://openalex.org/W2142845314","https://openalex.org/W2149684865","https://openalex.org/W2161453060","https://openalex.org/W6633839448","https://openalex.org/W6675354903","https://openalex.org/W6679997144","https://openalex.org/W6681124392","https://openalex.org/W6683656150"],"related_works":["https://openalex.org/W2751920613","https://openalex.org/W2415164632","https://openalex.org/W2238349241","https://openalex.org/W2355668701","https://openalex.org/W2370453500","https://openalex.org/W2079402849","https://openalex.org/W2359717995","https://openalex.org/W1561334777","https://openalex.org/W2338045944","https://openalex.org/W2354233396"],"abstract_inverted_index":{"Automatic":[0],"classification":[1,25,62],"of":[2,8,16,26,32,35,63,75,81,102,113,120,136,147,158],"documents":[3,36,65,82,114,150,160],"is":[4,145,164],"an":[5,52],"important":[6],"area":[7],"research":[9],"with":[10],"many":[11,44],"applications":[12],"in":[13,43,152,161],"the":[14,30,61,79,105,133,156,162],"fields":[15],"document":[17],"searching,":[18],"forensics":[19],"and":[20,70,93],"others.":[21],"Methods":[22],"to":[23,98,128,131],"perform":[24],"text":[27],"rely":[28],"on":[29,60],"existence":[31],"a":[33,73,111,117],"sample":[34,48,112,124],"whose":[37],"class":[38],"labels":[39],"are":[40],"known.":[41],"However,":[42],"situations,":[45],"obtaining":[46],"this":[47],"may":[49],"not":[50],"be":[51,126],"easy":[53],"(or":[54],"even":[55,151],"possible)":[56],"task.":[57],"We":[58,138],"focus":[59],"unlabelled":[64],"into":[66,83],"two":[67],"classes:":[68],"relevant":[69,121,149],"irrelevant,":[71],"given":[72],"topic":[74],"interest.":[76],"By":[77],"dividing":[78],"set":[80,135],"buckets":[84,163],"(for":[85],"instance,":[86],"answers":[87],"returned":[88],"by":[89],"different":[90],"search":[91],"engines),":[92],"using":[94],"association":[95],"rule":[96],"mining":[97],"find":[99],"common":[100],"sets":[101],"words":[103],"among":[104],"buckets,":[106],"we":[107],"can":[108,125],"efficiently":[109],"obtain":[110],"that":[115,142],"has":[116],"large":[118],"percentage":[119,157],"ones.":[122],"This":[123],"used":[127],"train":[129],"models":[130],"classify":[132],"entire":[134],"documents.":[137],"prove,":[139],"via":[140],"experimentation,":[141],"our":[143],"method":[144],"capable":[146],"filtering":[148],"adverse":[153],"conditions":[154],"where":[155],"irrelevant":[159],"relatively":[165],"high.":[166]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}