{"id":"https://openalex.org/W2157874634","doi":"https://doi.org/10.1145/2661829.2662060","title":"On Efficient Meta-Level Features for Effective Text Classification","display_name":"On Efficient Meta-Level Features for Effective Text Classification","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2157874634","doi":"https://doi.org/10.1145/2661829.2662060","mag":"2157874634"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2662060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2662060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","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/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":true,"raw_author_name":"Sergio Canuto","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001156386","display_name":"Thiago Salles","orcid":"https://orcid.org/0000-0003-2165-1999"},"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":"Thiago Salles","raw_affiliation_strings":["Federal Universito of Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal Universito of Minas Gerais, Belo Horizonte, 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/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"],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Federal University of Goias, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Goias, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087565388","display_name":"Leonardo Rocha","orcid":"https://orcid.org/0000-0002-4913-4902"},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Rocha","raw_affiliation_strings":["Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil","institution_ids":["https://openalex.org/I166595947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113640902","display_name":"Gabriel Ramos","orcid":null},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel Ramos","raw_affiliation_strings":["Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil","institution_ids":["https://openalex.org/I166595947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010487704","display_name":"Luiz Marcos Garcia Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-7735-5630"},"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":"Luiz Gon\u00e7alves","raw_affiliation_strings":["Federal University of Minas Gerais, Minas Gerais, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024659734","display_name":"Thierson Couto Rosa","orcid":"https://orcid.org/0000-0001-7117-3994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thierson Rosa","raw_affiliation_strings":["Informatics Institute, Goi\u00e2nia, Brazil"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, Goi\u00e2nia, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033070469","display_name":"Wellington S. Martins","orcid":"https://orcid.org/0000-0002-9641-2565"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Wellington Martins","raw_affiliation_strings":["Federal University of Goi\u00e1s, Goi\u00e2nia, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Goi\u00e1s, Goi\u00e2nia, Brazil","institution_ids":["https://openalex.org/I68106152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5046683090"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85411043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1709","last_page":"1718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.7150353193283081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723749995231628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5523236989974976},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5245107412338257},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.520749568939209},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5075880289077759},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4797343313694},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46460407972335815},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45414894819259644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45000365376472473},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4264526963233948},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33363234996795654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150353193283081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723749995231628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5523236989974976},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5245107412338257},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.520749568939209},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5075880289077759},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4797343313694},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46460407972335815},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45414894819259644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45000365376472473},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4264526963233948},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33363234996795654},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1145/2661829.2662060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2662060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7659367281","display_name":null,"funder_award_id":"0800 61 96 97","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7886827187","display_name":null,"funder_award_id":"+55 61 2022 6801","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W66588809","https://openalex.org/W129586823","https://openalex.org/W1487016832","https://openalex.org/W1533179050","https://openalex.org/W1956559956","https://openalex.org/W1980749268","https://openalex.org/W2021632899","https://openalex.org/W2023294425","https://openalex.org/W2050338028","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2118585731","https://openalex.org/W2124592110","https://openalex.org/W2135813353","https://openalex.org/W2145241906","https://openalex.org/W2150102617","https://openalex.org/W2153758664","https://openalex.org/W2160648405","https://openalex.org/W2170096781","https://openalex.org/W2264580665","https://openalex.org/W3001645704","https://openalex.org/W3018357277","https://openalex.org/W3100344990","https://openalex.org/W6631984995","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,22,33,36,39,44,58,76,97,100,110,125,128,139,153,160],"problem":[4],"of":[5,48,60,62,69,74,99,155,163],"automatically":[6],"learning":[7],"to":[8,64,117,170],"classify":[9],"texts":[10],"by":[11],"exploiting":[12],"information":[13],"derived":[14,20,31],"from":[15,21,32,57],"meta-level":[16,29,102,120,141],"features":[17,19,30,71,103,121,158,164],"(i.e.,":[18],"original":[23,77,161],"bag-of-words":[24],"representation).":[25],"We":[26,149],"propose":[27],"new":[28,82],"class":[34],"distribution,":[35],"entropy":[37],"and":[38,86,159],"within-class":[40],"cohesion":[41],"observed":[42],"in":[43,124,175],"k":[45],"nearest":[46],"neighbors":[47],"a":[49,81],"given":[50],"test":[51],"document":[52],"x,":[53],"as":[54,56],"well":[55],"distribution":[59],"distances":[61],"x":[63],"these":[65],"neighbors.":[66],"The":[67],"set":[68,162,173],"proposed":[70,101,123,129],"is":[72,104],"capable":[73],"transforming":[75],"feature":[78,172],"space":[79],"into":[80],"one,":[83],"potentially":[84],"smaller":[85],"more":[87,147],"informed.":[88],"Experiments":[89],"performed":[90],"with":[91],"several":[92],"standard":[93],"datasets":[94],"demonstrate":[95,151],"that":[96,152],"effectiveness":[98],"not":[105],"only":[106],"much":[107,146],"superior":[108,116],"than":[109,138],"traditional":[111],"bag-of-word":[112],"representation":[113],"but":[114],"also":[115,150],"other":[118],"state-of-art":[119],"previously":[122],"literature.":[126],"Moreover,":[127],"meta-features":[130],"can":[131],"be":[132],"computed":[133],"about":[134],"three":[135],"times":[136],"faster":[137],"existing":[140],"ones,":[142],"making":[143],"our":[144,156],"proposal":[145],"scalable.":[148],"combination":[154],"meta":[157],"produce":[165],"significant":[166],"improvements":[167],"when":[168],"compared":[169],"each":[171],"used":[174],"isolation.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}