{"id":"https://openalex.org/W1966503583","doi":"https://doi.org/10.1145/1007730.1007740","title":"A multistrategy approach for digital text categorization from imbalanced documents","display_name":"A multistrategy approach for digital text categorization from imbalanced documents","publication_year":2004,"publication_date":"2004-06-01","ids":{"openalex":"https://openalex.org/W1966503583","doi":"https://doi.org/10.1145/1007730.1007740","mag":"1966503583"},"language":"en","primary_location":{"id":"doi:10.1145/1007730.1007740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007730.1007740","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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":null,"display_name":"M. Dolores del Castillo","orcid":null},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"M. Dolores del Castillo","raw_affiliation_strings":["Instituto de Autom\u00e1tica Industrial (CSIC), Madrid, Spain","Instituto de Automatica Industrial (CSIC), Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Autom\u00e1tica Industrial (CSIC), Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Instituto de Automatica Industrial (CSIC), Madrid, Spain","institution_ids":["https://openalex.org/I134820265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082399828","display_name":"J. Ignacio Serrano","orcid":"https://orcid.org/0000-0002-9333-1305"},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Ignacio Serrano","raw_affiliation_strings":["Instituto de Autom\u00e1tica Industrial (CSIC), Madrid, Spain","Instituto de Automatica Industrial (CSIC), Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Autom\u00e1tica Industrial (CSIC), Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Instituto de Automatica Industrial (CSIC), Madrid, Spain","institution_ids":["https://openalex.org/I134820265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4905,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.98541835,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"1","first_page":"70","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9865999817848206,"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":0.9775000214576721,"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":0.8827075958251953},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6954832673072815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6056265830993652},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5864213109016418},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5254132747650146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.519025444984436},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.48086172342300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8827075958251953},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6954832673072815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6056265830993652},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5864213109016418},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5254132747650146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.519025444984436},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.48086172342300415},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1007730.1007740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007730.1007740","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.98.6892","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.98.6892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigkdd.org/explorations/issues/6-1-2004-06/serrano.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1481482547","https://openalex.org/W1504694836","https://openalex.org/W1507179106","https://openalex.org/W1549887922","https://openalex.org/W1563062065","https://openalex.org/W1592212241","https://openalex.org/W1593317353","https://openalex.org/W1596324102","https://openalex.org/W1619226191","https://openalex.org/W1639032689","https://openalex.org/W1692713333","https://openalex.org/W1718004567","https://openalex.org/W2033709196","https://openalex.org/W2043772506","https://openalex.org/W2053629277","https://openalex.org/W2070867367","https://openalex.org/W2087327261","https://openalex.org/W2098162425","https://openalex.org/W2118020653","https://openalex.org/W2125055259","https://openalex.org/W2132513611","https://openalex.org/W2158823144","https://openalex.org/W2170654002","https://openalex.org/W2435251607","https://openalex.org/W2560674852","https://openalex.org/W3023540311","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"The":[0,21,44,87],"goal":[1],"of":[2,78,102,107,114],"the":[3,73,76,79,100,105,112,115],"research":[4],"described":[5],"here":[6],"is":[7],"to":[8,33,40],"develop":[9],"a":[10,48,67,91],"multistrategy":[11],"classifier":[12],"system":[13,22,74,88],"that":[14,95],"can":[15],"be":[16],"used":[17],"for":[18,36],"document":[19],"categorization.":[20],"automatically":[23],"discovers":[24],"classification":[25,68],"patterns":[26],"by":[27,81],"applying":[28,82],"several":[29],"empirical":[30],"learning":[31],"methods":[32],"different":[34],"representations":[35],"preclassified":[37],"documents":[38],"belonging":[39],"an":[41],"imbalanced":[42],"sample.":[43],"learners":[45,80,103,108],"work":[46],"in":[47],"parallel":[49],"manner,":[50],"where":[51],"each":[52],"learner":[53],"carries":[54],"out":[55],"its":[56],"own":[57],"feature":[58],"selection":[59],"based":[60],"on":[61,90],"evolutionary":[62,83],"techniques":[63,84],"and":[64,110],"then":[65],"obtains":[66],"model.":[69],"In":[70],"classifying":[71],"documents,":[72],"combines":[75],"predictions":[77],"as":[85],"well.":[86],"relies":[89],"modular,":[92],"flexible":[93],"architecture":[94],"makes":[96],"no":[97],"assumptions":[98],"about":[99],"design":[101],"or":[104],"number":[106],"available":[109],"guarantees":[111],"independence":[113],"thematic":[116],"domain.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}