{"id":"https://openalex.org/W2795240784","doi":"https://doi.org/10.1109/tkde.2018.2820051","title":"A Thorough Evaluation of Distance-Based Meta-Features for Automated Text Classification","display_name":"A Thorough Evaluation of Distance-Based Meta-Features for Automated Text Classification","publication_year":2018,"publication_date":"2018-03-27","ids":{"openalex":"https://openalex.org/W2795240784","doi":"https://doi.org/10.1109/tkde.2018.2820051","mag":"2795240784"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2820051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2820051","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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":"https://openalex.org/A5046683090","display_name":"S\u00e9rgio Canuto","orcid":"https://orcid.org/0000-0003-2973-4158"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sergio Canuto","raw_affiliation_strings":["Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-2973-4158","affiliations":[{"raw_affiliation_string":"Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091429779","display_name":"Daniel Xavier de Sousa","orcid":"https://orcid.org/0000-0002-9426-9988"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel Xavier Sousa","raw_affiliation_strings":["Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andre Goncalves","raw_affiliation_strings":["Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2075-3363","affiliations":[{"raw_affiliation_string":"Depto. de Ci\u00eancia da Computa\u00e7\u00e3o, Federal University of Minas Gerais, Belo Horizonte-MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024659734","display_name":"Thierson Couto Rosa","orcid":"https://orcid.org/0000-0001-7117-3994"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR","SK"],"is_corresponding":false,"raw_author_name":"Thierson Couto Rosa","raw_affiliation_strings":["Institute of Informatics, Federal University of Goi\u00e1s, Goi\u00e2nia"],"raw_orcid":"https://orcid.org/0000-0001-7117-3994","affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Goi\u00e1s, Goi\u00e2nia","institution_ids":["https://openalex.org/I68106152","https://openalex.org/I4210152232"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5481,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94139599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":"12","first_page":"2242","last_page":"2256"},"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":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","score":0.9941999912261963,"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/overfitting","display_name":"Overfitting","score":0.8688381910324097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8382469415664673},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.7236454486846924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939319729804993},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.541377604007721},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5304405689239502},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.515629231929779},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48529142141342163},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42743125557899475},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4238553047180176},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4199891984462738},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3981422483921051},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13478979468345642}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8688381910324097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382469415664673},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7236454486846924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939319729804993},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.541377604007721},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5304405689239502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.515629231929779},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48529142141342163},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42743125557899475},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4238553047180176},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4199891984462738},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3981422483921051},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13478979468345642},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2018.2820051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2820051","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322904","display_name":"Financiadora de Estudos e Projetos","ror":"https://ror.org/030w99567"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W187357405","https://openalex.org/W190437827","https://openalex.org/W1480376833","https://openalex.org/W1487016832","https://openalex.org/W1502140970","https://openalex.org/W1533179050","https://openalex.org/W1560107318","https://openalex.org/W1661871015","https://openalex.org/W1965350272","https://openalex.org/W1972676371","https://openalex.org/W1979495886","https://openalex.org/W2022637272","https://openalex.org/W2040622444","https://openalex.org/W2050338028","https://openalex.org/W2057194219","https://openalex.org/W2059861826","https://openalex.org/W2085830763","https://openalex.org/W2091342063","https://openalex.org/W2101234009","https://openalex.org/W2109293916","https://openalex.org/W2114535528","https://openalex.org/W2118585731","https://openalex.org/W2128065064","https://openalex.org/W2135813353","https://openalex.org/W2145241906","https://openalex.org/W2153758664","https://openalex.org/W2157874634","https://openalex.org/W2170096781","https://openalex.org/W2295077356","https://openalex.org/W2435251607","https://openalex.org/W2536532331","https://openalex.org/W2911964244","https://openalex.org/W2994964425","https://openalex.org/W4205470728","https://openalex.org/W4255449644","https://openalex.org/W6607623206","https://openalex.org/W6607693206","https://openalex.org/W6629238926","https://openalex.org/W6633497745","https://openalex.org/W6636914306","https://openalex.org/W6675354045","https://openalex.org/W6677656871","https://openalex.org/W6684873705","https://openalex.org/W6717827561","https://openalex.org/W6771627385"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4295122168","https://openalex.org/W3155717344","https://openalex.org/W1770458422","https://openalex.org/W4283736627","https://openalex.org/W4308755723","https://openalex.org/W1543940884"],"abstract_inverted_index":{"We":[0,129,167,182],"address":[1],"the":[2,20,31,43,49,65,77,82,98,105,111,116,119,142,155,164],"problem":[3],"of":[4,79,84,100,107,118,144,163,180,187],"automatically":[5],"learning":[6],"to":[7,47,103,122,148,176],"classify":[8],"texts":[9],"by":[10,146],"exploiting":[11],"information":[12],"derived":[13,18],"from":[14,19],"meta-features,":[15,35],"i.e.,":[16],"features":[17],"original":[21,50],"bag-of-words":[22],"representation.":[23],"Specifically,":[24],"we":[25,96],"provide":[26],"an":[27],"in-depth":[28],"analysis":[29],"on":[30,42],"recently":[32],"proposed":[33],"distance-based":[34],"a":[36,54,123],"data":[37],"engineering":[38],"technique":[39],"that":[40,138,189],"relies":[41],"distance":[44],"between":[45],"documents":[46],"transform":[48],"feature":[51],"space":[52,67],"into":[53],"new":[55],"one,":[56],"potentially":[57],"smaller":[58],"and":[59,72,89,132],"more":[60],"informed.":[61],"Despite":[62],"its":[63],"potential,":[64],"meta-feature":[66,136],"may":[68],"be":[69],"unnecessarily":[70],"complex":[71],"highly":[73],"dimensional,":[74],"which":[75],"increases":[76,90],"tendency":[78],"overfitting,":[80],"limits":[81],"application":[83],"meta-features":[85,108,121,145,188],"in":[86,195],"different":[87,178],"contexts,":[88],"computational":[91],"costs.":[92],"In":[93],"this":[94],"work,":[95],"propose":[97],"use":[99,169],"multi-objective":[101],"strategies":[102,172],"reduce":[104,141],"number":[106,143],"while":[109,151],"maximizing":[110],"classification":[112,127,156,193],"effectiveness,":[113,157],"when":[114],"considering":[115],"adequacy":[117],"selected":[120],"particular":[124],"dataset":[125],"or":[126,153],"method.":[128],"present":[130],"effective":[131],"efficient":[133],"proposals":[134],"for":[135],"selection":[137,171],"can":[139,190],"substantially":[140],"up":[147],"89":[149],"percent":[150],"keeping":[152],"improving":[154],"something":[158],"not":[159],"possible":[160],"with":[161],"any":[162],"evaluated":[165],"baselines.":[166],"also":[168],"our":[170],"as":[173],"evaluation":[174],"tools":[175],"analyze":[177],"combinations":[179,186],"meta-features.":[181],"found":[183],"very":[184],"compact":[185],"achieve":[191],"high":[192],"effectiveness":[194],"most":[196],"datasets,":[197],"despite":[198],"their":[199],"peculiarities.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}